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. 3-GEMMASCOPE-RES-16K
    6. 5816
    Prev
    Next
    INDEX
    Explanations

    elements related to board games and grid coordinate systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.66
    expandindo
    -0.63
    Diweddarwch
    -0.61
    oa̍t
    -0.58
    MigrationBuilder
    -0.58
    Brainz
    -0.58
    цездатний
    -0.57
    ("}\
    -0.56
     jspb
    -0.54
     دیکھیے
    -0.54
    POSITIVE LOGITS
     coordinates
    0.79
    CGRectMake
    0.71
    BlockPos
    0.70
     Coordinates
    0.69
    帖最后由
    0.69
    LLocation
    0.67
    IntoConstraints
    0.66
    Coordinates
    0.65
    coordinates
    0.63
     coordon
    0.63
    Activations Density 0.381%

    No Known Activations