© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9900
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reflection or manifestation of concepts and states

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

    reflected in evidence

    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
    ibase
    -0.48
    abetta
    -0.42
    RoutingModule
    -0.42
     ')[
    -0.41
     ")[
    -0.41
    めの
    -0.40
     Maier
    -0.39
     Freedman
    -0.39
    Europ
    -0.38
    ']").
    -0.38
    POSITIVE LOGITS
     reflected
    0.72
     clearest
    0.70
    +#+
    0.70
    MessageOf
    0.55
     through
    0.53
     clearer
    0.52
     través
    0.51
    ViewFeatures
    0.51
     wyra
    0.50
     ExecuteAsync
    0.50
    Activations Density 0.085%

    No Known Activations