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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 314
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.52
    المشاركات
    -0.49
    notin
    -0.48
     FBref
    -0.48
     Abt
    -0.46
    VideoCapture
    -0.46
    %@
    -0.46
    ật
    -0.45
    setAction
    -0.45
     aguda
    -0.44
    POSITIVE LOGITS
     score
    0.78
     scoring
    0.76
     scores
    0.76
     Score
    0.75
    scores
    0.75
    Scores
    0.74
    score
    0.74
     Scores
    0.73
    SequentialGroup
    0.73
    Scoring
    0.73
    Activations Density 0.101%

    No Known Activations