© 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. 12897
    Prev
    Next
    INDEX
    Explanations

    negative impacts and complexities in various contexts

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

    completeness

    np_acts-logits-general · gemini-2.0-flash

    completeness or entirety

    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
    IntoConstraints
    -0.47
    出版年
    -0.45
    OGND
    -0.40
    ChildScrollView
    -0.39
    viaf
    -0.38
     виправивши
    -0.37
    chle
    -0.36
     Tran
    -0.36
     Maz
    -0.36
     bár
    -0.36
    POSITIVE LOGITS
     outright
    0.90
     altogether
    0.80
     gänzlich
    0.75
     downright
    0.71
     entirely
    0.70
    干脆
    0.69
     вовсе
    0.69
     completely
    0.69
     zupełnie
    0.67
     вообще
    0.66
    Activations Density 0.587%

    No Known Activations