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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8684
    Prev
    Next
    INDEX
    Explanations

    end-of-line comments in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    PostInfinity
    -0.47
     Biôgrafia
    -0.46
    wantErr
    -0.41
     falleció
    -0.39
    cancelButton
    -0.38
     institucional
    -0.38
     fallecimiento
    -0.38
     murieron
    -0.38
    JpaRepository
    -0.37
     saveiro
    -0.37
    POSITIVE LOGITS
    httphttps
    0.90
     فريبيس
    0.54
    hline
    0.54
    存于互联网档案馆
    0.53
    tvguidetime
    0.52
    VersionUID
    0.51
    .*")]
    0.50
     referenties
    0.48
    LikeLike
    0.48
    (...)
    0.48
    Activations Density 0.038%

    No Known Activations