Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 16378
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistical data points from a study or report

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

    journals or publications

    np_acts-logits-general · gemini-2.0-flash

    journal citations and volumes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.72
     שוליים
    -0.64
    #+#
    -0.59
     ZAP
    -0.58
     <",
    -0.58
     isInitialized
    -0.57
    Przypisy
    -0.57
     يتيمه
    -0.56
    </tfoot>
    -0.55
     okuyayım
    -0.54
    POSITIVE LOGITS
    ConstraintMaker
    0.79
    دانشنامهٔ
    0.77
    ┻
    0.61
    Попис
    0.54
    stylers
    0.51
    ContentAlignment
    0.50
    فاده
    0.49
    tım
    0.49
     asesinado
    0.47
     Roskov
    0.46
    Activations Density 0.306%

    No Known Activations