© 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. 38876
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "SL" which likely refers to a specific term or concept relevant in the context

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

    SL followed by common abbreviations/words

    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
     Mathis
    -0.48
    <strong>
    -0.46
    nóstico
    -0.45
    0
    -0.45
    ichter
    -0.44
     незавершена
    -0.44
     Hartman
    -0.43
    getdata
    -0.43
    Tikang
    -0.43
    ennis
    -0.43
    POSITIVE LOGITS
     SL
    2.20
    SL
    1.88
     sl
    1.30
     Sl
    1.29
    Sl
    1.17
    sl
    1.16
     Sla
    0.98
     SLA
    0.98
     Sli
    0.93
    Sli
    0.90
    Activations Density 0.006%

    No Known Activations