© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9071
    Prev
    Next
    INDEX
    Explanations

    references to controversial or offensive content

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

    Offensive, explicit, or taboo contents

    np_acts-logits-general · gemini-2.0-flash

    explicit or sexual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    oa̍t
    -0.40
    AndEndTag
    -0.37
    tagHelperRunner
    -0.34
    elseif
    -0.33
     essentielles
    -0.32
     colonia
    -0.32
    CloseOperation
    -0.31
     efficaces
    -0.31
    ródło
    -0.31
    jalá
    -0.31
    POSITIVE LOGITS
    RTEE
    0.59
    SharedDtor
    0.52
     censored
    0.50
     sexuality
    0.50
     nudity
    0.49
    Porn
    0.48
     censor
    0.48
    parsedMessage
    0.48
     taboo
    0.48
    IsMutable
    0.48
    Activations Density 0.342%

    No Known Activations