© 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. 22-GEMMASCOPE-RES-16K
    11. 5876
    Prev
    Next
    INDEX
    Explanations

    mentions of organizational titles and roles in relation to announcements or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.86
    rungsseite
    -0.75
     kasarigan
    -0.71
    MLLoader
    -0.68
    Vidite
    -0.64
    addContainerGap
    -0.63
     архивлан
    -0.61
     CanadaChoose
    -0.56
     चीज़ों
    -0.56
    twimg
    -0.54
    POSITIVE LOGITS
     ممن
    0.30
    qtype
    0.30
    Ken
    0.30
    eterangan
    0.30
    찰
    0.28
    Brasil
    0.28
    Jeff
    0.28
     olay
    0.27
    Arsenal
    0.27
    ríguez
    0.27
    Activations Density 0.348%

    No Known Activations