© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5537
    Prev
    Next
    INDEX
    Explanations

    references to job opportunities and recruitment processes

    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
    setVerticalGroup
    -0.54
    tanleria
    -0.50
    Архівовано
    -0.45
    windowFixed
    -0.43
     propOrder
    -0.42
    ագրություններ
    -0.42
    WriteAttribute
    -0.42
    assertSame
    -0.40
    цездатний
    -0.40
    AutoField
    -0.40
    POSITIVE LOGITS
     consideration
    1.65
     consider
    1.52
     considering
    1.51
     CONSIDER
    1.44
    考虑
    1.41
    consider
    1.39
     Consideration
    1.38
    considering
    1.35
    Consider
    1.34
     considerar
    1.32
    Activations Density 0.864%

    No Known Activations