© 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. 2-GEMMASCOPE-RES-16K
    11. 2290
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the components or structures of a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.77
    kuuta
    -0.70
     pulumi
    -0.67
     forceps
    -0.67
    Tikang
    -0.67
    bner
    -0.66
     Aps
    -0.63
    ̀i
    -0.62
    SharedCtor
    -0.62
    bigskip
    -0.61
    POSITIVE LOGITS
     consist
    2.89
     consists
    2.88
     consisted
    2.75
     consisting
    2.75
     consiste
    2.12
     comprised
    1.82
     terdiri
    1.80
     består
    1.78
     composed
    1.73
     comprising
    1.61
    Activations Density 0.133%

    No Known Activations