© 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. 20-GEMMASCOPE-RES-131K
    11. 121695
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or lack of clarity

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

    questions about what and whether

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    CodedInputStream
    -0.52
    참고
    -0.44
    posedge
    -0.41
    駅前
    -0.41
    inerja
    -0.39
    extAlignment
    -0.39
     praktijk
    -0.38
     Bin
    -0.38
    imageshack
    -0.38
    VideoCapture
    -0.37
    POSITIVE LOGITS
     how
    0.66
     whether
    0.65
     why
    0.62
     WHETHER
    0.57
     what
    0.56
     HOW
    0.47
    OCCURRED
    0.47
    httphttps
    0.47
     varför
    0.46
     WHY
    0.46
    Activations Density 0.111%

    No Known Activations