© 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. 31-GEMMASCOPE-RES-16K
    11. 2696
    Prev
    Next
    INDEX
    Explanations

    elements related to collaborative effort and interpersonal relationships

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

    the word "and" connecting related concepts or ideas in professional and motivational contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     etc
    -0.48
    erçe
    -0.43
     hikers
    -0.43
     singers
    -0.41
     pamphlets
    -0.39
    Ibid
    -0.39
    Poems
    -0.39
     nurses
    -0.38
     waiters
    -0.38
     asteroids
    -0.38
    POSITIVE LOGITS
     enjoyment
    0.65
     responsibility
    0.61
     inspiration
    0.58
     profitability
    0.58
    __*/
    0.57
    تفصیلات
    0.57
     expertise
    0.57
     responsiveness
    0.56
     capability
    0.56
     capabilities
    0.55
    Activations Density 0.501%

    No Known Activations