© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 28167
    Prev
    Next
    INDEX
    Explanations

    bulleted lists containing significant information or points of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Galafold, approvals, pipeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isNullOrEmpty
    -0.47
    </u>
    -0.46
     arquitect
    -0.44
    ArgumentParser
    -0.43
     architectural
    -0.41
    emplacement
    -0.41
    ("")]
    -0.37
     avoient
    -0.37
    )]=
    -0.37
     manger
    -0.37
    POSITIVE LOGITS
     •
    1.52
    ••••
    1.15
    •••
    1.06
    ••
    1.03
     ••
    0.91
    .•
    0.87
    ~•
    0.80
    )•
    0.77
     ·
    0.69
     ⚫
    0.69
    Activations Density 0.003%

    No Known Activations