Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9419
    Prev
    Next
    INDEX
    Explanations

    numerical arguments and evidence, specifically structured as reasons or findings supporting a claim

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

    enumerated lists that begin with "First" or similar ordinal markers followed by periods.

    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
    Życiorys
    -0.46
    meden
    -0.45
    __*/
    -0.45
     bevor
    -0.41
    MigrationBuilder
    -0.40
     vapours
    -0.39
     preceded
    -0.38
    หลัง
    -0.37
     surla
    -0.37
     intervene
    -0.36
    POSITIVE LOGITS
     secondly
    1.38
     Secondly
    1.23
    Secondly
    1.21
     firstly
    1.11
    Firstly
    1.09
     second
    1.09
     Firstly
    1.06
     first
    1.03
     Second
    0.98
    second
    0.93
    Activations Density 0.559%

    No Known Activations