Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2245
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical measurements and characteristics in a scientific context

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

    medical and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chemically
    -0.39
    eqn
    -0.36
     jsPsych
    -0.35
    (&:
    -0.35
    żesz
    -0.34
     Gallimard
    -0.34
     AspNetCore
    -0.33
     química
    -0.33
    eraard
    -0.32
    ModelAdmin
    -0.31
    POSITIVE LOGITS
    +:+
    0.55
    تفصیلات
    0.52
    Tarih
    0.52
    bibfield
    0.50
    فایل‌لار
    0.49
     Autorisations
    0.49
     SCOPE
    0.47
     Lipa
    0.47
    AddField
    0.47
    oa̍t
    0.47
    Activations Density 0.371%

    No Known Activations