Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56465
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ring" in various contexts related to mechanical or structural elements

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

    words starting with ring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )})
    -0.48
     DV
    -0.48
     })
    
    -0.46
    bst
    -0.46
    Dade
    -0.46
    '])
    
    -0.45
     Unavailable
    -0.45
     Fab
    -0.44
     Fabio
    -0.43
     Fifty
    -0.43
    POSITIVE LOGITS
     ring
    1.16
     Ring
    1.12
    Ring
    1.06
     RING
    1.02
     rings
    0.99
     Rings
    0.98
     bague
    0.94
    ring
    0.92
    Rings
    0.92
     anillo
    0.91
    Activations Density 0.011%

    No Known Activations