© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 90837
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" used frequently in lists or connections

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

    section headings after 'and'

    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
     fallu
    -0.39
    postIndex
    -0.37
    executable
    -0.36
     Landschafts
    -0.35
     olsa
    -0.33
     desert
    -0.32
    ever
    -0.32
    ]]
    -0.32
     esclusivamente
    -0.32
     "
    -0.32
    POSITIVE LOGITS
     EconPapers
    0.74
     Autorisations
    0.69
     referrerpolicy
    0.65
    قایناقلار
    0.57
    MemoryWarning
    0.55
    脚注の使い方
    0.55
    WireFormatLite
    0.54
     lenker
    0.54
     ब्रेकडाउन
    0.54
    vábbi
    0.53
    Activations Density 0.042%

    No Known Activations