© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 11044
    Prev
    Next
    INDEX
    Explanations

    potential outcomes and scenarios related to possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.82
     Affiliations
    -0.81
     ALA
    -0.74
     azzurro
    -0.73
    Tus
    -0.73
    DoubleQuotes
    -0.72
    ReusableCell
    -0.71
    unas
    -0.69
    GraphicsUnit
    -0.69
     Malk
    -0.69
    POSITIVE LOGITS
     could
    1.46
     COULD
    1.45
     Could
    1.33
    could
    1.31
    Could
    1.23
     would
    1.13
     pudiera
    1.07
     WOULD
    1.06
     potentially
    1.04
     might
    1.04
    Activations Density 0.087%

    No Known Activations