© 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. 65295
    Prev
    Next
    INDEX
    Explanations

    variables and their values in code, especially those prefixed with 'x', 'y', and 'z'

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

    #define macros

    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
    ]}>
    -0.45
     дописавши
    -0.41
    >(),
    -0.40
    )))),
    -0.39
     OMITBAD
    -0.38
     \\[
    -0.37
     Rat
    -0.37
    ;'>
    -0.36
    ']){
    -0.35
    >>;
    -0.35
    POSITIVE LOGITS
    enderror
    0.60
     ſein
    0.55
     purpoſe
    0.54
     desmotivaciones
    0.51
     Wiktionnaire
    0.50
     poffible
    0.50
     quelcon
    0.49
    Personendaten
    0.49
     wiſſen
    0.48
     Geiſt
    0.48
    Activations Density 0.013%

    No Known Activations