© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 4435
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to molecular biology and genetic studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    
    -1.26
    ?')
    -1.25
    )";
    
    -1.24
     Мексичка
    -1.20
    ++
    
    -1.19
    []
    
    -1.18
    __':
    
    -1.16
    AddTagHelper
    -1.15
     ModelExpression
    -1.15
    $")
    -1.14
    POSITIVE LOGITS
    .
    3.19
    。
    1.54
    ).
    1.48
    ."
    1.35
    .”
    1.32
    .
    
    1.31
    .\\
    1.25
    ।
    1.23
    !
    1.22
    ".
    1.22
    Activations Density 13.786%

    No Known Activations