© 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. 3-GEMMASCOPE-RES-16K
    6. 10459
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical correlation analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMG
    -0.65
     newName
    -0.65
    ίδι
    -0.63
     بيها
    -0.62
    hematics
    -0.61
    devamını
    -0.60
     ASM
    -0.60
    ιού
    -0.60
    panou
    -0.59
     getB
    -0.59
    POSITIVE LOGITS
     correlation
    2.73
     Correlation
    2.43
     correlations
    2.40
    Correlation
    2.28
    correlation
    2.26
     Correlations
    2.18
     correlated
    2.02
     correlate
    1.95
     correl
    1.88
    correlated
    1.80
    Activations Density 0.176%

    No Known Activations