© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 60104
    Prev
    Next
    INDEX
    Explanations

    references to "stakes" in a context that implies risk or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stakes are high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILDREN
    -0.52
     doInBackground
    -0.48
    EmployeeId
    -0.47
     Councilman
    -0.46
     polymorph
    -0.46
     backpacks
    -0.46
     CMV
    -0.46
    дивиду
    -0.46
     polymers
    -0.45
    Councillor
    -0.45
    POSITIVE LOGITS
    stakes
    2.08
     stakes
    2.08
     Stakes
    1.94
     stake
    1.03
     Stake
    0.95
    stake
    0.87
    AKES
    0.83
    Stake
    0.75
     enjeux
    0.75
     staked
    0.69
    Activations Density 0.006%

    No Known Activations