© 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. 18-GEMMASCOPE-RES-16K
    11. 1772
    Prev
    Next
    INDEX
    Explanations

    elements related to questioning and dialogue interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Dialogue or conversation snippets

    np_acts-logits-general · gemini-2.0-flash

    names followed by titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.86
     мәкал
    -0.82
    ftagPool
    -0.79
    +#+#
    -0.76
     المعيارى
    -0.76
    esserts
    -0.73
    writeFieldEnd
    -0.73
    LLocation
    -0.73
    IntoConstraints
    -0.71
    featureID
    -0.70
    POSITIVE LOGITS
    [
    0.53
    Unknown
    0.52
     Unknown
    0.50
    一同
    0.50
     unison
    0.47
     unknown
    0.47
    ???:
    0.47
     [
    0.46
    (
    0.45
    }")]
    0.44
    Activations Density 0.164%

    No Known Activations