© 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. 22-GEMMASCOPE-RES-16K
    11. 10119
    Prev
    Next
    INDEX
    Explanations

    statistical data regarding toxicological effects and concentrations related to substances

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    AndroidJUnit
    -0.46
    RTLR
    -0.46
     يتيمه
    -0.44
    enumii
    -0.44
    LookAnd
    -0.42
     Meksiku
    -0.42
    μως
    -0.40
     >=",
    -0.40
    Ӕ
    -0.40
    CDCl
    -0.40
    POSITIVE LOGITS
     concentrations
    0.58
     Concentrations
    0.52
     concentration
    0.50
     Dosis
    0.48
     CWE
    0.47
     thresholds
    0.46
     dosis
    0.46
     rates
    0.44
    -------
    0.44
     niveaux
    0.43
    Activations Density 1.074%

    No Known Activations