© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 5837
    Prev
    Next
    INDEX
    Explanations

    references to the pronouns "we," "you," and "I" indicating a focus on interpersonal communication or relationships

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

    ensuring proper actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     sembler
    -0.51
    obviously
    -0.51
     mungkin
    -0.48
     geralmente
    -0.48
     apparently
    -0.48
     tentu
    -0.48
    seamnă
    -0.48
     Seem
    -0.47
     diharapkan
    -0.47
     evidentemente
    -0.47
    POSITIVE LOGITS
     properly
    0.68
     adequately
    0.62
     stays
    0.60
    properly
    0.59
     proper
    0.56
     adequate
    0.55
    Proper
    0.53
     sufficiently
    0.52
     Properly
    0.50
     appropriately
    0.50
    Activations Density 0.030%

    No Known Activations