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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5275
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structural components in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     '\\;'
    -0.88
    ſicht
    -0.87
     Normdatei
    -0.87
     ſind
    -0.85
     незавершена
    -0.84
    IsContent
    -0.83
    niſſe
    -0.83
     queſta
    -0.79
    MigrationBuilder
    -0.79
    intios
    -0.79
    POSITIVE LOGITS
     Procu
    0.33
    draw
    0.30
    ])
    0.29
    )))
    0.29
    );
    0.28
    Draw
    0.28
    ']))
    0.28
    ]));
    
    0.28
    ]))
    0.28
    ))))
    0.27
    Activations Density 0.006%

    No Known Activations