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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6635
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of relevance or connection to a specific topic

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

    [Something/Nothing/Anything] to do with

    np_acts-logits-general · gemini-2.0-flash

    nothing to do with

    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
    yyj
    -0.51
    stuhl
    -0.51
    BASEPATH
    -0.49
    gef
    -0.49
    ρεύ
    -0.46
    []
    -0.45
    acoustic
    -0.45
     mại
    -0.45
    odar
    -0.44
     ab
    -0.44
    POSITIVE LOGITS
     unrelated
    0.95
     related
    0.88
     relates
    0.88
     kasarigan
    0.81
     relaciona
    0.80
    Билгалдахарш
    0.78
     unconnected
    0.77
    related
    0.77
     Zusammenhang
    0.75
     relacionados
    0.75
    Activations Density 0.124%

    No Known Activations