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. 3267
    Prev
    Next
    INDEX
    Explanations

    titles and references to creative works or media

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

    quoted text and titles of creative works (books, stories, songs, documentaries).

    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
    IntoConstraints
    -0.82
    tagHelperRunner
    -0.67
    httphttps
    -0.66
     Numerade
    -0.65
     nahilalakip
    -0.62
     AssemblyCulture
    -0.59
    styleType
    -0.57
    ConstraintMaker
    -0.57
    Personensuche
    -0.57
     Chwiliwch
    -0.55
    POSITIVE LOGITS
    The
    0.57
     The
    0.57
    Beyond
    0.56
     Beyond
    0.55
     beyond
    0.53
    Lessons
    0.52
    Where
    0.50
    beyond
    0.50
    Making
    0.49
     Making
    0.49
    Activations Density 0.280%

    No Known Activations