© 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. 9-GEMMASCOPE-RES-131K
    11. 55686
    Prev
    Next
    INDEX
    Explanations

    mentions of constructive feedback and community contributions

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

    constructive, productive, quality, meaningful communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gole
    -0.36
    WriteTagHelper
    -0.36
     croy
    -0.36
     EnglishChoose
    -0.35
    voyez
    -0.34
     fian
    -0.34
    Appear
    -0.34
    펴
    -0.33
    gdx
    -0.33
    mpä
    -0.33
    POSITIVE LOGITS
    quality
    0.60
     constructive
    0.59
     productive
    0.59
     quality
    0.58
     meaningful
    0.57
    productive
    0.56
     Productive
    0.55
     useful
    0.54
     worthwhile
    0.53
    useful
    0.52
    Activations Density 0.279%

    No Known Activations