© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 214
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical representations

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

    Followed by parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    understanding attempt sampling fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
     
    -1.36
    1
    -1.27
    ↵
    -1.26
    ,
    -1.23
     (
    -1.23
    <eos>
    -1.22
    ↵↵
    -1.21
    2
    -1.19
    .
    -1.18
    ...
    -1.16
    POSITIVE LOGITS
     Theſe
    2.36
     Monfieur
    2.18
     myſelf
    2.18
     Efq
    2.17
     itſelf
    2.09
     Мексичка
    1.94
     purpoſe
    1.82
     bezeichneter
    1.82
     raiſ
    1.81
     Anſ
    1.79
    Activations Density 10.689%

    No Known Activations