© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5460
    Prev
    Next
    INDEX
    Explanations

    detailed mentions of legal assessments and rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases with "reason" or explanatory conclusions following "that" or similar constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    the phrase "alone" when it follows specific words or phrases, particularly in formal or technical contexts where it emphasizes exclusivity or limitation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases that signal justification, causation, or methodological basis in an argument (stating reasons, grounds, bases, or means).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.35
    时候
    -0.33
    udahkan
    -0.30
    führende
    -0.29
    Conclusie
    -0.28
     virke
    -0.28
     labios
    -0.27
    ใจ
    -0.27
    EnumType
    -0.26
    putInt
    -0.26
    POSITIVE LOGITS
     alone
    3.89
    alone
    3.11
     ALONE
    2.92
     Alone
    2.89
    Alone
    2.53
     allein
    2.44
     alleine
    2.39
     alene
    2.34
     seul
    1.97
     saja
    1.95
    Activations Density 0.760%

    No Known Activations