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. 21-GEMMASCOPE-RES-16K
    6. 10703
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and relationships in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.73
     BoxFit
    -0.72
     كومونز
    -0.69
    MLLoader
    -0.68
    StoryboardSegue
    -0.65
    GraphicsUnit
    -0.65
    richTextPanel
    -0.65
    UserScript
    -0.65
    KommentareTeilen
    -0.63
    يكب
    -0.63
    POSITIVE LOGITS
     península
    0.41
     Antwort
    0.35
     отве
    0.33
     drauf
    0.30
    Lily
    0.30
     cardíaca
    0.29
     veder
    0.29
     πάν
    0.28
     vacía
    0.28
     doing
    0.28
    Activations Density 0.762%

    No Known Activations