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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13758
    Prev
    Next
    INDEX
    Explanations

    references to "solutions" and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
     Efq
    -0.90
     BorderRadius
    -0.81
    WriteAttribute
    -0.79
    cheque
    -0.76
     ISNI
    -0.75
    zieży
    -0.72
     craw
    -0.72
    󠁬
    -0.71
     Majefty
    -0.70
    herzog
    -0.70
    POSITIVE LOGITS
     solutions
    1.87
     Solutions
    1.73
     solution
    1.69
     Solution
    1.64
    Solutions
    1.64
     SOLUTION
    1.53
    Solution
    1.51
    solutions
    1.51
     SOLUTIONS
    1.50
    solution
    1.43
    Activations Density 0.113%

    No Known Activations