© 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. 18-GEMMASCOPE-RES-16K
    11. 15221
    Prev
    Next
    INDEX
    Explanations

    instances of significant negative results or outcomes

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

    Follows a capitalized word or abbreviation

    np_acts-logits-general · gemini-2.0-flash

    Community Services Specialized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -2.82
    </h1>
    -0.68
    ViewFeatures
    -0.67
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.67
    AndEndTag
    -0.65
     […]
    -0.64
    منبع
    -0.64
    </blockquote>
    -0.61
    "}";
    -0.61
     BIBLIO
    -0.59
    POSITIVE LOGITS
     Saltar
    0.66
    ()?;
    0.62
     uſed
    0.57
    findpost
    0.56
    niająca
    0.56
    NewUrlParser
    0.54
    InputTagHelper
    0.54
     purpoſe
    0.53
     houſe
    0.53
     Vikipedi
    0.53
    Activations Density 0.175%

    No Known Activations