© 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. 9633
    Prev
    Next
    INDEX
    Explanations

    occurrences of the number nine and its variants

    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
    findpost
    -0.51
    帖最后由
    -0.49
    literals
    -0.47
    ViewInit
    -0.46
    scalatest
    -0.46
    ANTLR
    -0.45
    ğraf
    -0.44
    LookAnd
    -0.44
    RunWith
    -0.44
    calaure
    -0.42
    POSITIVE LOGITS
     sense
    0.43
    tut
    0.42
     насељу
    0.38
    fromCharCode
    0.38
     Wunder
    0.38
    sense
    0.38
     mierda
    0.38
    ️⃣
    0.37
    Vidite
    0.37
    月份
    0.37
    Activations Density 0.967%

    No Known Activations