© 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. 5780
    Prev
    Next
    INDEX
    Explanations

    intensifiers and adverbs expressing strong opinions or feelings

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

    Follows intensifiers "really" or "just."

    np_acts-logits-general · gemini-2.0-flash

    really/just + verb

    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
    ’
    -1.03
    '
    -0.95
     themselves
    -0.87
    themselves
    -0.79
    $'
    -0.68
    '");
    -0.67
    '">
    -0.65
     herself
    -0.65
    '}>
    -0.63
     himself
    -0.63
    POSITIVE LOGITS
     noDo
    0.85
    TagMode
    0.83
    complexContent
    0.76
    ConstraintMaker
    0.74
     am
    0.73
     wonder
    0.73
     ModelExpression
    0.71
    webElementXpaths
    0.69
     disambiguazione
    0.67
    HomeAsUpEnabled
    0.66
    Activations Density 0.081%

    No Known Activations