© 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. 10283
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and data types

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

    both, respectively, alike

    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
     snippetHide
    -0.63
     незавершена
    -0.59
    AndroidJUnit
    -0.59
    #
    -0.57
    //
    -0.57
     ComVisible
    -0.57
    oa̍t
    -0.56
     समीक्षाएं
    -0.55
    +#+
    -0.54
    NewUrlParser
    -0.53
    POSITIVE LOGITS
     respectively
    0.57
     both
    0.55
    respectively
    0.51
     respectivamente
    0.51
     begge
    0.50
     alike
    0.50
     respectivement
    0.46
    両方
    0.45
     között
    0.44
     ambos
    0.42
    Activations Density 0.206%

    No Known Activations