© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7815
    Prev
    Next
    INDEX
    Explanations

    financial figures related to projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     usually
    -0.34
    statistik
    -0.33
     Usually
    -0.33
    月は
    -0.29
     comportamento
    -0.29
    Herkunft
    -0.28
    ActionCreators
    -0.28
     gebeten
    -0.27
     unterwegs
    -0.27
    StructEnd
    -0.27
    POSITIVE LOGITS
     construction
    1.18
     redevelopment
    1.12
    construction
    1.08
    Construction
    1.02
     renovations
    1.01
     plans
    0.99
     constructing
    0.98
     renovation
    0.95
    Plans
    0.95
    planned
    0.93
    Activations Density 0.595%

    No Known Activations