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-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9340
    Prev
    Next
    INDEX
    Explanations

    references to factors influencing research outcomes and community involvement in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResponseWriter
    -0.35
     Vic
    -0.31
    Vic
    -0.30
    Triggered
    -0.29
     gericht
    -0.29
    usercontent
    -0.29
     Puro
    -0.28
    fy
    -0.28
    vic
    -0.28
    以
    -0.27
    POSITIVE LOGITS
     contribution
    0.71
     inclusion
    0.66
    inclusion
    0.64
    volvement
    0.62
     contribut
    0.61
    contribution
    0.61
     contribución
    0.60
     aanwezig
    0.60
     contributor
    0.59
     inclusión
    0.59
    Activations Density 1.619%

    No Known Activations