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. 11-GEMMASCOPE-RES-16K
    6. 13998
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to accountability and procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -1.22
    RenderAtEndOf
    -1.11
     AssemblyCulture
    -1.08
     itſelf
    -1.02
     '\\;'
    -0.99
    Viitteet
    -0.97
     Theſe
    -0.96
     كومونز
    -0.95
    ьаж
    -0.92
     Autorizaciones
    -0.92
    POSITIVE LOGITS
    ,
    0.67
    .
    0.61
    ..
    0.49
     «
    0.46
     so
    0.46
    EC
    0.46
     g
    0.46
    ...
    0.44
     '
    0.44
     (
    0.44
    Activations Density 0.986%

    No Known Activations