© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 799
    Prev
    Next
    INDEX
    Explanations

    clauses and questions that indicate suggestions or inquiries in a discussion

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

    Punctuation, symbols, and uncommon capitalization

    np_acts-logits-general · gemini-2.0-flash

    numbers, symbols, and specific tokens that end phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.67
    Билгалдахарш
    -0.59
    السكان
    -0.57
    Viited
    -0.46
     gepubliceerd
    -0.44
    Filmografie
    -0.43
    DIPSETTING
    -0.42
     consultato
    -0.40
    Décès
    -0.40
    солю
    -0.40
    POSITIVE LOGITS
    反正
    0.47
    Portale
    0.45
    AnchorTagHelper
    0.44
     Doing
    0.42
     would
    0.42
    évaluateur
    0.40
     идея
    0.40
     thereby
    0.40
     wtedy
    0.40
    Idea
    0.39
    Activations Density 0.598%

    No Known Activations