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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6645
    Prev
    Next
    INDEX
    Explanations

    references to specific sporting events and competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ब्रेकडाउन
    -0.60
     للمعارف
    -0.59
    ScopeManager
    -0.57
    IsContent
    -0.57
    webElementXpaths
    -0.56
     motivadoras
    -0.54
     otomatig
    -0.54
     nervioso
    -0.54
    saraba
    -0.54
     elettrico
    -0.53
    POSITIVE LOGITS
     hypo
    0.36
     stakes
    0.36
     prize
    0.35
    休
    0.35
     macro
    0.35
     conferences
    0.35
     بم
    0.35
     challenge
    0.35
     important
    0.35
     cash
    0.33
    Activations Density 0.036%

    No Known Activations