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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1385
    Prev
    Next
    INDEX
    Explanations

    terms related to events, releases, and updates in entertainment and media

    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
    contentLoaded
    -0.71
    AddHtmlAttribute
    -0.71
    ]--;
    -0.68
    IntoConstraints
    -0.66
    homonymie
    -0.63
    ########.
    -0.59
    WebServlet
    -0.58
     '{@
    -0.56
    nestjs
    -0.55
     noqa
    -0.55
    POSITIVE LOGITS
     debuted
    0.70
     officially
    0.67
     debuts
    0.65
     scheduled
    0.58
     estreia
    0.58
     kicks
    0.57
     hit
    0.57
    officially
    0.57
     premiered
    0.56
     hits
    0.56
    Activations Density 0.211%

    No Known Activations