© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 560
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to problem-solving and suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreExecute
    -0.45
    VIAF
    -0.42
    acherous
    -0.38
    Rptr
    -0.38
    EReference
    -0.35
     Congrats
    -0.35
    хіво
    -0.33
    orghe
    -0.31
    rugu
    -0.31
    ruik
    -0.31
    POSITIVE LOGITS
     solution
    3.50
    solution
    3.16
     solutions
    3.13
     Solution
    2.97
    Solution
    2.95
     solución
    2.94
     SOLUTION
    2.88
     solução
    2.80
     solve
    2.75
    solutions
    2.75
    Activations Density 1.667%

    No Known Activations