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. 22-GEMMASCOPE-RES-16K
    6. 7889
    Prev
    Next
    INDEX
    Explanations

    elements related to formatted whitespace or layout structure

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

    Followed by "P" and a number

    np_acts-logits-general · gemini-2.0-flash

    legal citations and technical terms

    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
    pulumi
    -0.56
     single
    -0.54
    ↵↵
    -0.50
     double
    -0.49
    BuildContext
    -0.48
     Single
    -0.46
    )}^{
    -0.46
    <eos>
    -0.45
    marvin
    -0.45
     mit
    -0.44
    POSITIVE LOGITS
    findpost
    0.90
     مشين
    0.81
    躇
    0.77
    évaluateur
    0.75
    Personensuche
    0.71
     متعلقه
    0.69
    tagHelperRunner
    0.67
     CreateTagHelper
    0.67
    ViewFeatures
    0.67
    BibitemShut
    0.66
    Activations Density 0.012%

    No Known Activations