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

    Neuronpedia

    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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 136
    Prev
    Next
    INDEX
    Explanations

    the word "whatever" and its variations in context

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

    the word "whatever" in various contexts, indicating a dismissive or indifferent tone

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

    whatever phrase starter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -1.04
    BeginContext
    -0.82
    TagMode
    -0.68
     Audiodateien
    -0.67
    OGND
    -0.67
    findpost
    -0.65
    UnitTesting
    -0.65
     Utf
    -0.62
     kaynağından
    -0.62
     LUMP
    -0.61
    POSITIVE LOGITS
     else
    1.06
     happens
    0.79
    kolwiek
    0.69
     happened
    0.67
    cinogen
    0.65
     floats
    0.65
    Else
    0.64
    VELOP
    0.63
    rrrrr
    0.63
    glades
    0.61
    Activations Density 0.017%

    No Known Activations