Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7277
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight reasons or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [
    -0.51
    **************
    -0.49
    [
    -0.47
     [*
    -0.45
     *
    -0.44
     [[
    -0.43
     &
    -0.42
     de
    -0.42
     Forst
    -0.42
    tabular
    -0.42
    POSITIVE LOGITS
     raisonnable
    0.78
     saveiro
    0.78
     démocr
    0.76
     citoy
    0.75
     pédagogique
    0.75
     pédagog
    0.73
    Consejos
    0.72
     sánchez
    0.72
     pegat
    0.71
     desmotivaciones
    0.71
    Activations Density 0.520%

    No Known Activations