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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14410
    Prev
    Next
    INDEX
    Explanations

    percentage-related formatting in text that indicates variable placeholders

    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
    IUrlHelper
    -0.80
     &___
    -0.67
    ViewFeatures
    -0.65
    LookAnd
    -0.63
    WritableDatabase
    -0.62
    RenderAtEndOf
    -0.61
    }');
    -0.61
    ScopeManager
    -0.59
    /');
    -0.59
    */),
    -0.58
    POSITIVE LOGITS
    SBATCH
    0.68
     alignItems
    0.53
     carab
    0.50
    s
    0.49
     Ambiental
    0.49
    AddTagHelper
    0.48
     Ketch
    0.48
    alignItems
    0.48
     Coconut
    0.48
    urysty
    0.48
    Activations Density 0.053%

    No Known Activations