© 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. 22-GEMMASCOPE-RES-16K
    11. 2487
    Prev
    Next
    INDEX
    Explanations

    JavaScript code elements and structures

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

    Javascript code snippets and console logs

    np_acts-logits-general · gemini-2.0-flash

    javascript code and functions

    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
     Ngb
    -0.58
     Norma
    -0.55
     calendriers
    -0.55
     medarbe
    -0.54
     Мексичка
    -0.54
    VersionUID
    -0.54
     căr
    -0.53
    ReusableCell
    -0.53
    consulté
    -0.52
     hjemme
    -0.52
    POSITIVE LOGITS
    console
    0.92
     console
    0.78
    };
    0.74
    var
    0.69
     var
    0.68
     };
    0.67
    '};
    0.66
    $('#
    0.62
    document
    0.61
     document
    0.61
    Activations Density 0.086%

    No Known Activations