© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 7380
    Prev
    Next
    INDEX
    Explanations

    phrases related to energy companies and their financial implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    łko
    -0.36
     양
    -0.35
     beginning
    -0.33
    hörigen
    -0.32
     vérité
    -0.29
    양
    -0.29
     really
    -0.29
     latter
    -0.29
     physical
    -0.28
     much
    -0.28
    POSITIVE LOGITS
    RegressionTest
    0.93
    rungsseite
    0.75
    tagHelperRunner
    0.69
    principalColumn
    0.65
    Tikang
    0.65
    aarrggbb
    0.64
    __":
    0.63
     NSCoder
    0.62
     Wicidata
    0.58
    __':
    0.58
    Activations Density 0.386%

    No Known Activations