© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1054
    Prev
    Next
    INDEX
    Explanations

    instances of the word "However," indicating a shift or contrast in the text

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

    "However"

    np_acts-logits-general · gemini-2.0-flash

    however,

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    resaid
    -0.64
     neceff
    -0.63
     createSlice
    -0.61
     dedans
    -0.60
     Majefty
    -0.60
    وانید
    -0.59
     ftate
    -0.58
    เลย
    -0.56
     occafion
    -0.56
     fhew
    -0.55
    POSITIVE LOGITS
     demikian
    0.80
     مرئيه
    0.73
    że
    0.65
     &___
    0.64
    ⓧ
    0.62
     much
    0.60
     autorytatywna
    0.58
    much
    0.56
    sidemargin
    0.56
     []:
    0.56
    Activations Density 0.079%

    No Known Activations