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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 3036
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and elements, particularly those related to sulfides and phosphors

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

    Chemical compounds containing "fluor" or "sulf"

    np_acts-logits-general · gemini-2.0-flash

    chlorides, sulfides, fluorides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षक
    -0.55
    μφωνα
    -0.53
    hasRole
    -0.52
    AnchorTagHelper
    -0.49
    OrFail
    -0.47
    olol
    -0.47
     Hauptstadt
    -0.46
    чков
    -0.45
     SUPPLIES
    -0.45
    ctools
    -0.44
    POSITIVE LOGITS
    لينكات
    0.57
     lenker
    0.54
     articol
    0.54
    hpur
    0.53
    xase
    0.53
    esModule
    0.52
     Ester
    0.50
    migrationBuilder
    0.50
     tuong
    0.49
    RetentionPolicy
    0.49
    Activations Density 0.403%

    No Known Activations