© 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. 11-GEMMASCOPE-RES-16K
    11. 6601
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only" and its related contexts, often focusing on exclusivity or singularity

    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
    Apre
    -0.49
     meta
    -0.45
     pula
    -0.45
     بلا
    -0.45
    وها
    -0.44
    naker
    -0.43
     учили
    -0.43
    viewType
    -0.43
    しまう
    -0.42
    ppa
    -0.42
    POSITIVE LOGITS
    CloseOperation
    0.94
     doInBackground
    0.92
     mapStateToProps
    0.79
    RenderAtEndOf
    0.69
    +#+#
    0.69
     defaultstate
    0.69
    Datuak
    0.67
    AnimationsModule
    0.67
     للاسماء
    0.66
    以外は
    0.65
    Activations Density 0.321%

    No Known Activations