© 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. 3-GEMMASCOPE-RES-16K
    11. 925
    Prev
    Next
    INDEX
    Explanations

    the word "slightly" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.74
    ColumnHeaders
    -0.63
     Rece
    -0.59
     aeruginosa
    -0.59
    conos
    -0.59
    jangkau
    -0.58
    躇
    -0.58
    onOptions
    -0.57
     ribos
    -0.57
     yoksa
    -0.56
    POSITIVE LOGITS
     slightly
    2.63
    slightly
    2.60
     Slightly
    2.44
    Slightly
    2.36
     slight
    2.18
    Slight
    2.03
     Slight
    1.97
     légèrement
    1.88
     ligeramente
    1.82
     leggermente
    1.79
    Activations Density 0.078%

    No Known Activations