© 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. 8241
    Prev
    Next
    INDEX
    Explanations

    elements related to conflict and resolution involving supernatural or dark themes

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

    Plot summaries or descriptions

    np_acts-logits-general · gemini-2.0-flash

    discover new secrets

    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
    LookAnd
    -0.72
     nahilalakip
    -0.70
    出版年
    -0.64
     opérateur
    -0.59
     kemarin
    -0.57
    Generally
    -0.56
    istoitu
    -0.56
     typically
    -0.55
     mencionar
    -0.55
     mentioning
    -0.54
    POSITIVE LOGITS
     discovers
    0.90
     discover
    0.78
     uncovering
    0.76
     secrets
    0.75
     uncover
    0.71
     unexpected
    0.71
     soon
    0.69
     discovery
    0.69
    discover
    0.69
     unexpectedly
    0.68
    Activations Density 0.285%

    No Known Activations