© 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. 31-GEMMASCOPE-RES-131K
    11. 65533
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thorough" and its variations

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

    completeness and depth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.74
     الرياضيه
    -0.64
    SequentialGroup
    -0.59
     CanadaChoose
    -0.57
    脚注の使い方
    -0.57
    addChild
    -0.56
    ⓧ
    -0.55
    addLast
    -0.53
    msgTypes
    -0.53
    PyExc
    -0.53
    POSITIVE LOGITS
    bred
    0.73
    fare
    0.60
    ness
    0.60
     Thorough
    0.59
     thorough
    0.53
    going
    0.53
    Thor
    0.46
    fares
    0.46
    ly
    0.45
     THOR
    0.45
    Activations Density 0.004%

    No Known Activations