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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 8772
    Prev
    Next
    INDEX
    Explanations

    key features and functionalities of e-commerce platforms

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

    Follows a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    sequence analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -1.37
     disambiguazione
    -1.30
    Personensuche
    -1.28
    MigrationBuilder
    -1.25
     للاسماء
    -1.23
     Wikispecies
    -1.14
    verwijspagina
    -1.11
     AssemblyCulture
    -1.09
     autorytatywna
    -1.08
    вгений
    -1.07
    POSITIVE LOGITS
    <strong>
    1.04
    <h2>
    0.99
    <b>
    0.96
     
    0.90
    <h3>
    0.88
    </blockquote>
    0.85
    </strong>
    0.82
    [toxicity=0]
    0.82
    </td>
    0.78
    <em>
    0.77
    Activations Density 0.922%

    No Known Activations