© 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. 13691
    Prev
    Next
    INDEX
    Explanations

    commands or phrases indicating the initiation of actions or processes

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

    "start" or its variations

    np_acts-logits-general · gemini-2.0-flash

    beginning of actions

    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
    욱
    -0.41
    y
    -0.39
     Tapatalk
    -0.39
     whom
    -0.39
    Vey
    -0.38
    HBox
    -0.38
     filePath
    -0.38
     JSON
    -0.38
    ↵↵↵↵
    -0.38
    i
    -0.37
    POSITIVE LOGITS
    start
    1.23
    Start
    1.23
     start
    1.20
    START
    1.16
     Start
    1.16
     START
    1.13
    starts
    1.10
    started
    1.05
     Starts
    1.03
    getStart
    1.02
    Activations Density 0.101%

    No Known Activations