© 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. 31-GEMMASCOPE-RES-16K
    11. 2654
    Prev
    Next
    INDEX
    Explanations

    descriptive features related to fashion and color patterns

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

    words and phrases describing visual patterns, textures, and decorative design elements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.56
    BASEPATH
    -0.52
    MemoryWarning
    -0.47
    InstrumentedTest
    -0.45
     enfans
    -0.45
     autorytatywna
    -0.44
     ſtate
    -0.44
    AndEndTag
    -0.44
    ьаж
    -0.43
    httphttps
    -0.42
    POSITIVE LOGITS
     pattern
    1.67
     patterns
    1.65
    pattern
    1.44
     patterned
    1.42
     Patterns
    1.39
     Pattern
    1.37
    patterns
    1.33
     PATTERN
    1.32
    Pattern
    1.30
     patterning
    1.27
    Activations Density 0.426%

    No Known Activations