© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1346
    Prev
    Next
    INDEX
    Explanations

    HTML and programming syntax elements related to user interface components

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

    HTML headings

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ništvo
    -0.55
    HomeAsUpEnabled
    -0.53
     kaarangay
    -0.49
    lccn
    -0.47
    ContentAsync
    -0.47
    PRWEB
    -0.46
     voordeel
    -0.45
    UnitTesting
    -0.45
    CppMethod
    -0.45
    GEBURTS
    -0.44
    POSITIVE LOGITS
    Попис
    0.41
     images
    0.37
     props
    0.37
     zeros
    0.35
     image
    0.35
    SharedDtor
    0.34
     klip
    0.34
     figure
    0.33
    erapeutics
    0.33
     sur
    0.33
    Activations Density 0.055%

    No Known Activations