© 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. 18-GEMMASCOPE-RES-16K
    11. 6283
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases associated with sports performance statistics

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

    "scored" or "scoring" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    sports scores and achievements

    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
    LLocation
    -0.60
    andafter
    -0.59
     bepaalde
    -0.55
     bestimmte
    -0.54
     المعيارى
    -0.54
    Portale
    -0.52
    certain
    -0.52
     somebody
    -0.51
     anum
    -0.51
    someone
    -0.51
    POSITIVE LOGITS
     three
    0.58
     estekak
    0.57
     two
    0.57
    VersionUID
    0.56
     impressively
    0.56
     four
    0.55
    adpleegd
    0.55
     a
    0.55
     impressive
    0.53
     unanimously
    0.53
    Activations Density 0.206%

    No Known Activations