© 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. 17985
    Prev
    Next
    INDEX
    Explanations

    research-oriented language focusing on new trends and developments in various fields

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

    current trends and developments

    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
    endsection
    -0.35
     «
    -0.30
    édie
    -0.29
    üme
    -0.26
     kek
    -0.26
    «
    -0.26
     العاده
    -0.26
     san
    -0.25
     zus
    -0.23
    〒
    -0.23
    POSITIVE LOGITS
    adpleegd
    0.66
    transQ
    0.64
     Issues
    0.62
    DotNetBar
    0.62
     desmotivaciones
    0.61
    ضايا
    0.60
     enjeux
    0.60
     professionnels
    0.59
     kasarigan
    0.58
     Professional
    0.57
    Activations Density 0.069%

    No Known Activations