© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12852
    Prev
    Next
    INDEX
    Explanations

    occurrences of player statistics and game outcomes in sports contexts

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

    Follows commas or periods

    np_acts-logits-general · gemini-2.0-flash

    words after punctuation/prepositions

    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
     Bewußt
    -0.62
    iſen
    -0.58
     pleaſure
    -0.55
     Verſ
    -0.55
    latego
    -0.54
    chränk
    -0.54
     plufieurs
    -0.52
     laſſen
    -0.52
     itſelf
    -0.52
    出版年
    -0.51
    POSITIVE LOGITS
    disposing
    0.44
    LookAnd
    0.40
    mlx
    0.38
     phút
    0.33
    complexType
    0.32
    大
    0.32
     triumphed
    0.32
    rizona
    0.31
     Despite
    0.30
    нь
    0.30
    Activations Density 0.090%

    No Known Activations