© 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. 9792
    Prev
    Next
    INDEX
    Explanations

    textual structures characterized by punctuation and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.89
     disambiguazione
    -0.69
     CallOverrides
    -0.66
     propOrder
    -0.66
    extAlignment
    -0.65
    躇
    -0.65
     ujednoznacz
    -0.64
    wiliwch
    -0.62
    期刊论文
    -0.62
    вгений
    -0.61
    POSITIVE LOGITS
    .”
    0.37
    The
    0.35
     demás
    0.33
    

    0.32
    Following
    0.31
    ”.
    0.29
    ixante
    0.29
    Last
    0.29
    Though
    0.28
    Unlike
    0.28
    Activations Density 0.108%

    No Known Activations