© 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. 5831
    Prev
    Next
    INDEX
    Explanations

    segments related to itemization or lists of products or concepts

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

    signature spell rank

    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
     للاسماء
    -0.70
    Atsauces
    -0.66
     informaciones
    -0.65
     varandra
    -0.65
     kasarigan
    -0.64
     ilustracja
    -0.63
     desmotivaciones
    -0.61
     miniaturka
    -0.59
     Toutefois
    -0.59
     møte
    -0.59
    POSITIVE LOGITS
     shitty
    0.81
     crappy
    0.77
     freaking
    0.70
     pretty
    0.69
    Honestly
    0.69
     fucking
    0.68
     FUCKING
    0.66
    Pretty
    0.65
    Anyways
    0.65
     insanely
    0.65
    Activations Density 0.079%

    No Known Activations