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

    Neuronpedia

    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. 14481
    Prev
    Next
    INDEX
    Explanations

    instances of explanation and storytelling

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

    the verb "show" or "explain" followed by "how".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    parsedMessage
    -0.39
     oprot
    -0.37
     Audiodateien
    -0.35
    zust
    -0.33
    IntoConstraints
    -0.32
    匿名使用者
    -0.31
    APORE
    -0.31
     âges
    -0.30
    шины
    -0.29
    씀
    -0.29
    POSITIVE LOGITS
     how
    3.64
     cómo
    2.58
    how
    2.56
    How
    2.41
     How
    2.33
     bagaimana
    2.31
     hvordan
    2.20
    如何
    2.09
     HOW
    2.06
     چگونه
    1.95
    Activations Density 1.111%

    No Known Activations