© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2047
    Prev
    Next
    INDEX
    Explanations

    references to notable figures or entities associated with intrigue or controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Throm
    -0.71
    >):
    -0.63
     оригіналу
    -0.63
     дописавши
    -0.63
    нансо
    -0.62
    fontaine
    -0.60
     Jericho
    -0.60
     throm
    -0.59
     thrombo
    -0.56
     zostać
    -0.56
    POSITIVE LOGITS
    aarrggbb
    0.77
    tagHelperRunner
    0.77
     Bon
    0.73
    Clik
    0.72
    SerializedSize
    0.71
    Bon
    0.68
    extAlignment
    0.67
    buzz
    0.67
    Buzz
    0.66
     Mel
    0.62
    Activations Density 0.599%

    No Known Activations