© 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. 38-GEMMASCOPE-RES-16K
    11. 7622
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of tasks, updates, or changes related to a process or item

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.71
    每一次
    -0.63
     annuelle
    -0.60
     GenerationType
    -0.59
    Annual
    -0.57
    每次
    -0.57
    aarrggbb
    -0.56
    annual
    -0.56
    bootstrapcdn
    -0.55
     &___
    -0.55
    POSITIVE LOGITS
     frequently
    0.93
     often
    0.82
     fairly
    0.79
     quite
    0.74
    frequently
    0.69
     Frequently
    0.69
    Frequently
    0.67
    บ
    0.65
     regularly
    0.63
     frequ
    0.63
    Activations Density 0.408%

    No Known Activations