Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 4988
    Prev
    Next
    INDEX
    Explanations

    text related to organizational planning and community support initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.94
     betweenstory
    -0.94
    évaluateur
    -0.76
     enfans
    -0.74
     avoient
    -0.74
     vectorielles
    -0.73
     pauv
    -0.69
    ########.
    -0.68
    horabuena
    -0.68
     étoient
    -0.66
    POSITIVE LOGITS
     weekly
    1.03
     Weekly
    0.83
     regularly
    0.82
    weekly
    0.79
     monthly
    0.77
     daily
    0.70
    Weekly
    0.69
     wöch
    0.67
     visits
    0.67
     quarterly
    0.66
    Activations Density 0.256%

    No Known Activations