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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45542
    Prev
    Next
    INDEX
    Explanations

    terms related to cosmetic and medical procedures, particularly those involving enhancement and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    roben
    -0.47
     ActivatedRoute
    -0.47
     kasarigan
    -0.46
    colar
    -0.46
    lanniksi
    -0.45
    endforeach
    -0.45
     Nij
    -0.45
    ɵɵ
    -0.44
    Vidite
    -0.43
    araj
    -0.43
    POSITIVE LOGITS
    crollView
    0.42
     elast
    0.41
    executeUpdate
    0.40
     elasticity
    0.40
     tightness
    0.39
    исленность
    0.39
    setVerticalGroup
    0.38
     pleaſure
    0.38
     stretch
    0.37
     kompres
    0.36
    Activations Density 0.009%

    No Known Activations