© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3965
    Prev
    Next
    INDEX
    Explanations

    verbs indicating states, actions, and abilities, particularly in the context of hypothesis or result descriptions

    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
    󠁢
    -0.67
    URLEncoder
    -0.65
     يتيمه
    -0.64
    ɫ
    -0.61
    cito
    -0.61
    opo
    -0.59
     igång
    -0.59
     unprotected
    -0.58
     cassa
    -0.57
    tellungs
    -0.57
    POSITIVE LOGITS
     propOrder
    0.80
    webElement
    0.79
     tartalomajánló
    0.78
     also
    0.74
    XmlAccessType
    0.73
     is
    0.70
    MigrationBuilder
    0.70
    DeleteBehavior
    0.69
    InjectAttribute
    0.64
     has
    0.63
    Activations Density 1.158%

    No Known Activations