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. 24357
    Prev
    Next
    INDEX
    Explanations

    words and names related to articulation and Arthur

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

    Arthur and articulation

    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
     незавершена
    -0.51
    }}}
    -0.49
    }<
    -0.47
    )<\
    -0.47
    ;'>
    -0.45
     })}
    -0.45
    '}>
    -0.44
    ')}
    -0.44
    })}
    -0.43
     />}
    -0.42
    POSITIVE LOGITS
     Arthur
    0.79
    Arthur
    0.71
    arthur
    0.71
     Artur
    0.71
     Art
    0.66
     Artic
    0.64
     articulation
    0.62
     arthur
    0.61
     Article
    0.61
     ART
    0.60
    Activations Density 0.011%

    No Known Activations