© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8815
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to scientific and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.77
     leſs
    -0.69
    
    -0.68
    phosa
    -0.67
    ſelves
    -0.66
    UrlResolution
    -0.65
    RegressionTest
    -0.64
    openqa
    -0.63
     समीक्षाएं
    -0.62
    település
    -0.61
    POSITIVE LOGITS
    expandindo
    0.63
    ValueStyle
    0.55
    LookAnd
    0.51
    HtmlAttribute
    0.47
    InSection
    0.46
    HomeAsUpEnabled
    0.46
    antMatchers
    0.43
     fatale
    0.42
     EClass
    0.42
    ftagPool
    0.42
    Activations Density 1.531%

    No Known Activations