© 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. 23-GEMMASCOPE-RES-16K
    11. 8880
    Prev
    Next
    INDEX
    Explanations

    statistical data related to patient populations and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vœ
    -0.49
     OkHttpClient
    -0.48
     CRITERIA
    -0.44
     Kriterien
    -0.43
    pecabe
    -0.43
     règne
    -0.43
     Privacidad
    -0.42
    UserScript
    -0.42
    holdet
    -0.41
    Erreferentziak
    -0.41
    POSITIVE LOGITS
    Autoritní
    0.59
    VIAF
    0.53
     omnibus
    0.47
    bison
    0.46
    bob
    0.45
    subsubsection
    0.44
     下午
    0.44
     Brookings
    0.43
    inaldi
    0.43
     OFDb
    0.43
    Activations Density 1.760%

    No Known Activations