© 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. 23-GEMMASCOPE-RES-16K
    11. 10448
    Prev
    Next
    INDEX
    Explanations

    terms that indicate opportunities or potential 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 @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeString
    -0.36
    Base
    -0.34
     apag
    -0.32
     lục
    -0.32
     yık
    -0.31
     Base
    -0.31
     names
    -0.30
     obsah
    -0.30
    ir
    -0.30
     base
    -0.30
    POSITIVE LOGITS
    Opportunity
    1.58
     opportunity
    1.57
     Opportunity
    1.52
    opportunity
    1.52
     OPPORTUNITY
    1.43
     opportunities
    1.34
     Opportunities
    1.34
    pportun
    1.31
    Opportunities
    1.30
    opportunities
    1.30
    Activations Density 0.088%

    No Known Activations