© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7232
    Prev
    Next
    INDEX
    Explanations

    elements related to social dynamics and personal relationships

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

    discourse-structuring signals in text—connectives, reporting/realization verbs, sentence-boundary punctuation, and list/question formatting that mark explanation, contrast, causation, or enumeration.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    sentence or clause boundaries, particularly where a new topic, character, or narrative element is being introduced.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iffance
    -0.78
     AssemblyCulture
    -0.77
    ſammen
    -0.75
    BibitemShut
    -0.75
    ſelben
    -0.72
    ſchen
    -0.70
    iſen
    -0.70
    
    -0.69
    <unused41>
    -0.68
    <unused79>
    -0.68
    POSITIVE LOGITS
     characters
    0.29
     highly
    0.26
    tahui
    0.25
     himself
    0.25
    userManager
    0.24
    plot
    0.24
     per
    0.23
     są
    0.23
     the
    0.23
     ri
    0.23
    Activations Density 0.076%

    No Known Activations