© 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 EvalsExportsAPI 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. 6944
    Prev
    Next
    INDEX
    Explanations

    key phrases highlighting the importance of critical aspects in various contexts

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

    that indicate importance or necessity

    np_acts-logits-general · gemini-2.0-flash

    importance and significance

    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
    AutoScaleMode
    -0.70
    migrationBuilder
    -0.66
    TagHelpers
    -0.61
    Espèce
    -0.59
     समीक्षाओं
    -0.58
    LookAnd
    -0.56
     //$
    -0.56
     autorytatywna
    -0.55
    Ārējās
    -0.55
    $​
    -0.53
    POSITIVE LOGITS
     important
    2.46
     critical
    2.32
     crucial
    2.26
     vital
    2.10
    important
    2.03
     essential
    1.99
    critical
    1.93
     vitally
    1.88
     key
    1.83
     Important
    1.83
    Activations Density 0.670%

    No Known Activations