© 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. 15-GEMMASCOPE-RES-16K
    11. 8837
    Prev
    Next
    INDEX
    Explanations

    contextual details about organizations, membership, or features related to a group or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.73
    StructEnd
    -0.70
    StoryboardSegue
    -0.69
     another
    -0.65
    Xna
    -0.65
     Waray
    -0.63
     betweenstory
    -0.62
    another
    -0.62
    PreferredItem
    -0.61
    astéroïdes
    -0.60
    POSITIVE LOGITS
     eligible
    0.56
    Eligible
    0.55
     qualify
    0.52
     concernés
    0.48
     Eligible
    0.48
    eligible
    0.48
     involved
    0.47
     createSlice
    0.45
    inclusive
    0.44
    対象
    0.43
    Activations Density 0.526%

    No Known Activations