© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13433
    Prev
    Next
    INDEX
    Explanations

    terms indicating solutions or methods to address problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     patterns
    -0.45
     amitié
    -0.44
     faptul
    -0.40
     Pattern
    -0.39
    Pattern
    -0.39
     pattern
    -0.39
     către
    -0.39
     acompanhar
    -0.38
     Patterns
    -0.38
    EFIAPI
    -0.38
    POSITIVE LOGITS
     solution
    3.84
    solution
    3.55
     Solution
    3.42
    Solution
    3.30
     SOLUTION
    3.17
     solutions
    3.13
     solución
    2.92
     soluzione
    2.81
    solutions
    2.81
     solução
    2.75
    Activations Density 0.197%

    No Known Activations