© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8929
    Prev
    Next
    INDEX
    Explanations

    statements or references to "this" or "that" in a contextual or definitional manner

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

    "This" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    This followed by is/was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.67
    CodeAttribute
    -0.55
     ModelExpression
    -0.55
    Especies
    -0.53
    arResult
    -0.52
    RegressionTest
    -0.51
    หน้านี้
    -0.51
    RenderAtEndOf
    -0.50
    哦
    -0.50
    游戏特色
    -0.49
    POSITIVE LOGITS
     is
    0.95
     was
    0.85
     certainly
    0.83
     means
    0.81
     includes
    0.79
     wasn
    0.78
     begs
    0.75
     isn
    0.71
     wiederum
    0.70
     may
    0.70
    Activations Density 0.229%

    No Known Activations