© 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. 560
    Prev
    Next
    INDEX
    Explanations

    key performance indicators and actions related to critical developments or significant changes in various contexts

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

    Word followed by "for" or "because"

    np_acts-logits-general · gemini-2.0-flash

    contrast words

    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
    AndEndTag
    -0.46
     ModelExpression
    -0.41
     visuales
    -0.39
     tendances
    -0.39
     negócio
    -0.38
     ennen
    -0.38
    cshtml
    -0.37
     onOptions
    -0.37
     sáb
    -0.35
    /**
    -0.35
    POSITIVE LOGITS
     trotzdem
    0.67
     dennoch
    0.65
     Trotzdem
    0.60
     ändå
    0.59
     Dennoch
    0.55
    writeFieldEnd
    0.54
     nevertheless
    0.53
     nonetheless
    0.52
    それでも
    0.50
    WaitGroup
    0.48
    Activations Density 0.428%

    No Known Activations