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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10674
    Prev
    Next
    INDEX
    Explanations

    AJAX-related code snippets and commands

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

    jQuery AJAX calls

    np_acts-logits-general · gemini-2.0-flash

    Javascript AJAX requests

    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
     CURIAM
    -0.71
     مرئيه
    -0.67
    spedes
    -0.59
    ună
    -0.57
    tagHelper
    -0.56
     autorytatywna
    -0.55
    èges
    -0.55
    pasti
    -0.53
     مشين
    -0.53
    ']],
    -0.52
    POSITIVE LOGITS
    dataType
    0.69
     dataType
    0.68
    async
    0.62
    datatype
    0.61
     async
    0.56
    xhr
    0.55
     datatype
    0.54
    beforeSend
    0.53
    WebMethod
    0.53
     XMLHttpRequest
    0.53
    Activations Density 0.095%

    No Known Activations