© 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. 65824
    Prev
    Next
    INDEX
    Explanations

    key phrases related to belief, truth, and perception

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

    thing or things

    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
    どの
    -0.34
    TemporalType
    -0.28
    dtypes
    -0.26
    zzard
    -0.25
    eterminate
    -0.25
     mous
    -0.25
    wiście
    -0.25
    ど
    -0.25
     ど
    -0.24
     tro
    -0.23
    POSITIVE LOGITS
     thing
    2.59
     things
    2.47
     something
    2.20
    thing
    2.09
    things
    2.06
     Things
    2.05
     coisa
    2.03
    Things
    1.98
     THING
    1.97
     cosas
    1.96
    Activations Density 0.358%

    No Known Activations