© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9216
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'won' and its variations, indicating success or victory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.89
     estekak
    -0.76
    colgante
    -0.71
     surla
    -0.69
    chaleco
    -0.69
     engraçadas
    -0.68
    pulseira
    -0.65
    AndEndTag
    -0.65
    ########.
    -0.65
    تقاوى
    -0.65
    POSITIVE LOGITS
    Past
    0.54
     won
    0.54
     Past
    0.51
    won
    0.50
     past
    0.50
     Vide
    0.49
     PS
    0.49
     ps
    0.48
     Ps
    0.47
    Video
    0.46
    Activations Density 0.302%

    No Known Activations