© 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. 40-GEMMASCOPE-RES-16K
    11. 5342
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical measures and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alguno
    -0.45
     InputDecoration
    -0.41
    tiéndose
    -0.40
    いくつか
    -0.39
     Algunos
    -0.39
     Either
    -0.38
    Others
    -0.38
    其他人
    -0.38
    Gambas
    -0.37
    енча
    -0.37
    POSITIVE LOGITS
     every
    3.59
    every
    3.05
    Every
    2.63
     Every
    2.59
     EVERY
    2.44
    EVERY
    2.39
     ogni
    2.14
     everything
    2.09
     setiap
    2.09
    ทุก
    1.94
    Activations Density 1.017%

    No Known Activations