© 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. 35-GEMMASCOPE-RES-16K
    11. 14112
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate leveraging opportunities or advantages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.54
     TextAlign
    -0.46
    SharedCtor
    -0.45
    GOTREF
    -0.44
    GTCX
    -0.43
     onBackPressed
    -0.42
    endphp
    -0.41
     resourceCulture
    -0.41
    AutoScaleMode
    -0.40
    addContainerGap
    -0.40
    POSITIVE LOGITS
     aprovechar
    1.96
     exploiting
    1.92
     aprovecha
    1.90
     aprove
    1.89
     exploit
    1.87
     exploited
    1.76
     capitalize
    1.73
     exploitation
    1.72
     memanfaatkan
    1.70
     Aprove
    1.61
    Activations Density 0.719%

    No Known Activations