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. 9221
    Prev
    Next
    INDEX
    Explanations

    discussion of renovations or changes in buildings and organizations

    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
     muualla
    -0.71
     utafitiHapana
    -0.54
    Composable
    -0.51
     useAppContext
    -0.51
    ajevo
    -0.51
    wpi
    -0.50
    jsonwebtoken
    -0.49
     fondation
    -0.49
    onViewCreated
    -0.49
    conectar
    -0.48
    POSITIVE LOGITS
     changes
    1.03
     change
    0.98
     Changes
    0.90
    changes
    0.87
     changements
    0.85
    Changes
    0.84
     cambios
    0.81
     changement
    0.79
     Change
    0.79
     alterations
    0.78
    Activations Density 0.701%

    No Known Activations