© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 380
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between different concepts or elements

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

    after coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    technical lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ))))
    -0.31
    AtIndex
    -0.31
     Gir
    -0.30
    …
    -0.30
     irra
    -0.30
    /
    -0.30
    Gdx
    -0.29
     Party
    -0.29
     COMP
    -0.29
     cup
    -0.28
    POSITIVE LOGITS
     Normdatei
    0.82
    IntoConstraints
    0.76
    الدراسه
    0.68
    httphttps
    0.68
    sizeCache
    0.68
    دانشنامهٔ
    0.65
     Exactos
    0.65
    TypedDataSet
    0.65
    stylers
    0.65
    ScopeManager
    0.63
    Activations Density 0.668%

    No Known Activations