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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12923
    Prev
    Next
    INDEX
    Explanations

    occurrences of ellipsis or variations of continuous sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }]
    
    -0.70
    rizona
    -0.68
    ]]:
    -0.67
     jsPsych
    -0.65
     HAV
    -0.64
    وردار
    -0.63
    []{"
    -0.62
    كر
    -0.62
     Haft
    -0.61
     Vergara
    -0.61
    POSITIVE LOGITS
    ldots
    1.78
     /\.
    0.96
    msgSender
    0.87
     /\.(
    0.72
    SBATCH
    0.72
     ucran
    0.68
     ceramica
    0.68
    nextProps
    0.68
     Libyan
    0.68
     تانيه
    0.68
    Activations Density 0.062%

    No Known Activations