© 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. 11-GEMMASCOPE-RES-16K
    6. 8923
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "breaking."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    adaptiveStyles
    -0.51
    htbp
    -0.39
     Langu
    -0.39
     Idy
    -0.39
    不及
    -0.38
     DbType
    -0.37
    mtd
    -0.36
     Logo
    -0.36
    議院
    -0.35
    ್ದ
    -0.35
    POSITIVE LOGITS
     break
    1.83
     Break
    1.72
     breaking
    1.70
    break
    1.69
     breaks
    1.65
    Break
    1.65
     BREAK
    1.63
     Breaking
    1.59
    Breaking
    1.57
     broke
    1.55
    Activations Density 0.204%

    No Known Activations