© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12379
    Prev
    Next
    INDEX
    Explanations

    references to shifts in organizational or personal structures

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

    Preceding a word indicating an organization

    np_acts-logits-general · gemini-2.0-flash

    leaving format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ướ
    -0.34
     (!$
    -0.31
    しかも
    -0.31
    supset
    -0.30
    vician
    -0.30
     contrast
    -0.29
     addition
    -0.28
     sou
    -0.28
     dig
    -0.28
     scattered
    -0.28
    POSITIVE LOGITS
     altogether
    1.09
    parsedMessage
    0.83
     abruptly
    0.80
     entirely
    0.78
     kokona
    0.75
    новниш
    0.74
     tartalomajánló
    0.73
     temporarily
    0.72
     completely
    0.72
     kvůli
    0.72
    Activations Density 0.564%

    No Known Activations