© 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. 0-GEMMASCOPE-RES-16K
    11. 7276
    Prev
    Next
    INDEX
    Explanations

    terms indicating something is fundamental or intrinsic in nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    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
    -0.79
    ponses
    -0.79
    waitKey
    -0.77
     oprot
    -0.75
     createState
    -0.75
    AnimationsModule
    -0.74
     complètes
    -0.73
     isInitialized
    -0.73
    (&:
    -0.73
     snippetHide
    -0.72
    POSITIVE LOGITS
     exactly
    0.57
     elsewhere
    0.54
     plenty
    0.54
    在
    0.52
     nearly
    0.52
    us
    0.51
    else
    0.51
    รา
    0.50
     temporarily
    0.50
     objectMapper
    0.49
    Activations Density 0.167%

    No Known Activations