© 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. 15740
    Prev
    Next
    INDEX
    Explanations

    negative sentiment indicators or phrases

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

    Followed by a number or letter

    np_acts-logits-general · gemini-2.0-flash

    foreign language constructs

    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
     Warne
    -0.58
     didReceive
    -0.56
     useSelector
    -0.54
    Dichlor
    -0.51
    AdapterFactory
    -0.51
     szóci
    -0.49
    jud
    -0.49
     Fein
    -0.48
     Schre
    -0.48
     Marchand
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.82
     pinulongan
    0.66
    #
    0.65
    shaped
    0.65
     EconPapers
    0.65
     дописавши
    0.64
    poň
    0.60
     shaped
    0.59
     Poincaré
    0.58
     NUKAT
    0.57
    Activations Density 0.442%

    No Known Activations