© 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. 0-GEMMASCOPE-RES-16K
    6. 3217
    Prev
    Next
    INDEX
    Explanations

    references to lectures and exhibits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hunger
    -0.51
     placement
    -0.51
     dye
    -0.50
     discharge
    -0.48
     fund
    -0.48
     bouw
    -0.48
     grant
    -0.46
     transport
    -0.46
     Placement
    -0.46
     draft
    -0.46
    POSITIVE LOGITS
    yyyy
    0.69
    yy
    0.66
     ProtoMessage
    0.65
    yyyyy
    0.60
     gynhyrchwyd
    0.54
    yyy
    0.53
    AutoScaleMode
    0.50
     noDo
    0.50
    parsedMessage
    0.50
    queryInterface
    0.48
    Activations Density 0.194%

    No Known Activations