© 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. 1-GEMMASCOPE-RES-16K
    11. 8166
    Prev
    Next
    INDEX
    Explanations

    specific coding terminology and function references in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ersatz
    -0.37
     Bourgeois
    -0.33
     Pedersen
    -0.31
     un
    -0.31
    hyrchwyd
    -0.31
     
    -0.30
     Coo
    -0.30
    dihydro
    -0.30
    withIdentifier
    -0.30
     Bes
    -0.29
    POSITIVE LOGITS
    xaml
    0.70
    xam
    0.65
    存于互联网档案馆
    0.63
     queſta
    0.62
    xdr
    0.59
    MigrationBuilder
    0.59
    Xeno
    0.59
     XG
    0.59
     Xtreme
    0.57
     ſind
    0.57
    Activations Density 1.575%

    No Known Activations