© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1832
    Prev
    Next
    INDEX
    Explanations

    code structure elements and import statements in programming languages

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

    code snippets with file import statements and module references.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Jîn
    -0.53
    RegistryLite
    -0.48
    RepeatedField
    -0.43
    WebControls
    -0.40
    gwt
    -0.40
    jspx
    -0.39
     ReactDOM
    -0.35
    ṯ
    -0.35
    GetAxis
    -0.34
    enumi
    -0.34
    POSITIVE LOGITS
    最快更新
    0.66
     nahilalakip
    0.60
    StoryboardSegue
    0.57
     <<<<<<<<<<<<<<
    0.50
     Tagged
    0.49
    帖最后由
    0.48
     للاسماء
    0.47
     médié
    0.46
    ########.
    0.45
     personnalisée
    0.44
    Activations Density 0.099%

    No Known Activations