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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2578
    Prev
    Next
    INDEX
    Explanations

    ordinal dates and numerical information

    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
    TypedDataSet
    -0.65
    enderror
    -0.63
    culable
    -0.57
     pkt
    -0.56
    IsMutable
    -0.55
    prepareStatement
    -0.54
     pyro
    -0.54
     pips
    -0.54
    protoimpl
    -0.54
    NLS
    -0.53
    POSITIVE LOGITS
     morning
    0.52
     couvercle
    0.49
     comigo
    0.49
     trône
    0.47
     monasterio
    0.47
     administrativo
    0.47
     feroit
    0.46
     ennemi
    0.46
     drapeau
    0.45
     enfans
    0.45
    Activations Density 0.095%

    No Known Activations