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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6446
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thrown" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.86
    ISupport
    -0.70
    IBarButtonItem
    -0.69
    הערות
    -0.67
    Explicación
    -0.66
     tỏ
    -0.65
    posedge
    -0.65
    seguida
    -0.64
    ConstraintMaker
    -0.64
     متحده
    -0.64
    POSITIVE LOGITS
     golden
    0.93
     Platinum
    0.86
     kicked
    0.85
    golden
    0.85
     Golden
    0.84
     Gold
    0.80
    Platinum
    0.79
     platinum
    0.78
    platinum
    0.78
    Gold
    0.77
    Activations Density 0.088%

    No Known Activations