© 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. 19-GEMMASCOPE-RES-16K
    11. 15422
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs and their syntactic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mapStateToProps
    -0.61
    yntaxException
    -0.60
     للمعارف
    -0.57
    bootstrapcdn
    -0.55
    OpenHelper
    -0.51
     ErrIntOverflow
    -0.51
    سام
    -0.51
    DockStyle
    -0.51
    fromJson
    -0.50
    mería
    -0.49
    POSITIVE LOGITS
     get
    1.04
    get
    0.85
     getter
    0.77
     Gets
    0.72
     ModelExpression
    0.71
    InjectAttribute
    0.70
     gets
    0.66
    geti
    0.64
     getting
    0.63
    tvguidetime
    0.62
    Activations Density 0.077%

    No Known Activations