© 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. 8982
    Prev
    Next
    INDEX
    Explanations

    discussions of statistical significance and comparisons in research data

    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
    ècie
    -0.61
    greja
    -0.50
    <!
    -0.50
    tiary
    -0.49
    HIP
    -0.47
     Doo
    -0.47
     XCTest
    -0.47
    oping
    -0.47
    URED
    -0.46
    amable
    -0.46
    POSITIVE LOGITS
     correspondingly
    1.19
     likewise
    1.08
     Likewise
    0.96
     altrett
    0.85
     accordingly
    0.85
    Likewise
    0.83
     similarly
    0.82
     ditto
    0.79
     Similarly
    0.78
     соответственно
    0.78
    Activations Density 0.745%

    No Known Activations