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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3462
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to criminal cases

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

    numerical quantities and amounts, particularly in legal and scientific contexts involving counts, doses, measurements, and factual data.

    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
    出版年
    -0.43
    tout
    -0.41
    微
    -0.40
    ště
    -0.40
    PYX
    -0.40
    Jäh
    -0.39
    bein
    -0.39
    底
    -0.39
     isim
    -0.39
     bea
    -0.39
    POSITIVE LOGITS
     instances
    0.64
     Aspekte
    0.59
     myſelf
    0.58
    instances
    0.56
    webElementXpaths
    0.55
     tilf
    0.53
     instance
    0.52
     Monfieur
    0.50
     esempi
    0.49
     møte
    0.49
    Activations Density 0.874%

    No Known Activations