Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15025
    Prev
    Next
    INDEX
    Explanations

    references to data storage and management or the organization of computational resources

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

    Code, copyright, or location information

    np_acts-logits-general · gemini-2.0-flash

    code lines and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     uova
    -0.53
     Italijani
    -0.52
    Étymologie
    -0.52
     Meksiku
    -0.51
     ProtoMessage
    -0.51
     réfrigérateur
    -0.51
     referenties
    -0.51
    خصة
    -0.50
    san
    -0.49
    tonode
    -0.48
    POSITIVE LOGITS
     line
    0.80
    line
    0.75
     filename
    0.70
    醐
    0.64
    LINE
    0.61
    linec
    0.60
    location
    0.59
     LINE
    0.59
    awtextra
    0.58
     Line
    0.58
    Activations Density 0.017%

    No Known Activations