© 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. 39-GEMMASCOPE-RES-16K
    11. 661
    Prev
    Next
    INDEX
    Explanations

    references to parking lots and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RepeatedField
    -0.39
    endwhile
    -0.36
    Eksterne
    -0.34
    gdx
    -0.34
     Reverso
    -0.33
    vertx
    -0.31
    AccessorTable
    -0.30
     sejauh
    -0.30
    alyptus
    -0.30
    дравству
    -0.30
    POSITIVE LOGITS
     lot
    3.36
     Lot
    3.03
    Lot
    3.02
     lots
    2.95
     Lots
    2.77
    lot
    2.75
    Lots
    2.69
    lots
    2.67
     LOT
    2.44
    LOT
    2.42
    Activations Density 0.657%

    No Known Activations