© 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. 12815
    Prev
    Next
    INDEX
    Explanations

    mentions of medical professionals and discussions around care or treatment

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

    did not, wouldn't, purportedly

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects tokens that are the prefix part of hyphenated compounds (tokens immediately before a hyphen).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     behaviour
    -0.52
     generalised
    -0.49
     favour
    -0.45
     colour
    -0.43
    COLOUR
    -0.43
     realised
    -0.42
     favours
    -0.42
     realise
    -0.42
     maximise
    -0.42
     kilometres
    -0.42
    POSITIVE LOGITS
     pleaſure
    0.79
     ſta
    0.77
     myſelf
    0.76
    ſelf
    0.73
     Anſ
    0.72
     itſelf
    0.71
     purpoſe
    0.69
    RTLR
    0.69
     houſe
    0.68
     faſt
    0.68
    Activations Density 0.704%

    No Known Activations