© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13421
    Prev
    Next
    INDEX
    Explanations

    structured elements related to navigation in a web interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cshtml
    -0.56
     relev
    -0.46
     المعيارى
    -0.45
    uitable
    -0.43
    +#+#
    -0.43
    httphttps
    -0.41
     ExecuteAsync
    -0.40
    ">//
    -0.40
     bVar
    -0.40
    jspx
    -0.38
    POSITIVE LOGITS
    SharedCtor
    0.66
    KURZBESCHREIBUNG
    0.66
    Portail
    0.64
    '}>
    0.64
    FieldBuilder
    0.64
    ⓧ
    0.63
    __":
    0.63
    AnimationsModule
    0.63
     незавершена
    0.62
    !*\
    0.62
    Activations Density 0.126%

    No Known Activations