© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 4788
    Prev
    Next
    INDEX
    Explanations

    mentions of stainless steel and its qualities or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.51
    oredCriteria
    -0.46
    tagHelperRunner
    -0.45
     мәкал
    -0.45
    StoryboardSegue
    -0.44
    فحة
    -0.43
      (
    -0.43
    PropertyChanging
    -0.43
    sonaro
    -0.42
    oplayer
    -0.42
    POSITIVE LOGITS
    lla
    1.15
    LLA
    1.13
    ller
    1.09
    llo
    1.05
    LLO
    1.00
    LLER
    0.95
    ella
    0.95
    llas
    0.94
    eller
    0.91
    lle
    0.91
    Activations Density 0.344%

    No Known Activations