© 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. 0-GEMMASCOPE-RES-16K
    11. 8853
    Prev
    Next
    INDEX
    Explanations

    counts and variations of items or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grüsse
    -0.70
     ostavi
    -0.63
     Gerechtigkeit
    -0.57
    eseorang
    -0.57
     Zweifel
    -0.57
     metų
    -0.55
     Económica
    -0.55
     Meksika
    -0.53
     Suiza
    -0.53
     Hidup
    -0.53
    POSITIVE LOGITS
     FontWeight
    0.71
     kinds
    0.70
     able
    0.65
     many
    0.62
     lots
    0.61
     different
    0.61
     rowspan
    0.61
    SEVER
    0.60
     sort
    0.59
     kind
    0.57
    Activations Density 0.398%

    No Known Activations