© 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. 41965
    Prev
    Next
    INDEX
    Explanations

    elements related to personal growth and self-discovery through experiences and practices

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

    pronoun followed by past verb

    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
     nincs
    -0.58
     bislang
    -0.56
     છે
    -0.55
     are
    -0.53
    currently
    -0.53
     actuellement
    -0.50
    maktadır
    -0.50
     Currently
    -0.50
     bisher
    -0.49
     είναι
    -0.49
    POSITIVE LOGITS
     was
    1.87
     did
    1.38
     were
    1.33
     wasn
    1.33
     had
    1.31
     gave
    1.31
     took
    1.29
     didn
    1.24
     went
    1.24
     became
    1.23
    Activations Density 6.305%

    No Known Activations