© 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. 10267
    Prev
    Next
    INDEX
    Explanations

    instances of code-related syntax and structures

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

    German database commands

    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
    humour
    -0.48
     informée
    -0.45
    Tribe
    -0.44
     المعيارى
    -0.44
     للاسماء
    -0.44
     vainilla
    -0.44
    windowFixed
    -0.44
     Ressources
    -0.43
     ressources
    -0.43
    locality
    -0.43
    POSITIVE LOGITS
    Personendaten
    0.57
    oredCriteria
    0.52
    Tikang
    0.47
     createSlice
    0.39
     onOptions
    0.38
    uesia
    0.36
     springfox
    0.35
    ymce
    0.35
    :✨
    0.34
     Detail
    0.34
    Activations Density 0.000%

    No Known Activations