© 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. 6220
    Prev
    Next
    INDEX
    Explanations

    numerical data or values related to scientific measurements or observations

    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
    MigrationBuilder
    -0.64
    ۱
    -0.64
    URLException
    -0.63
    httphttps
    -0.60
     &___
    -0.58
    脚注の使い方
    -0.55
    RectangleBorder
    -0.54
     المعيارى
    -0.54
     كومونز
    -0.54
    EndInit
    -0.54
    POSITIVE LOGITS
    xx
    0.47
    XX
    0.45
     hundred
    0.37
    Forty
    0.36
    hundred
    0.33
    ÍST
    0.33
    OO
    0.32
    6
    0.32
    forty
    0.32
    7
    0.32
    Activations Density 1.492%

    No Known Activations