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. 21-GEMMASCOPE-RES-16K
    6. 413
    Prev
    Next
    INDEX
    Explanations

    phrases related to the application and automation of technologies in medicine and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     using
    -0.83
    using
    -0.71
     utilizzando
    -0.68
     createSlice
    -0.66
    Using
    -0.64
     menggunakan
    -0.63
     Using
    -0.62
     USING
    -0.61
     usando
    -0.61
    Use
    -0.61
    POSITIVE LOGITS
    hibli
    0.69
    ]--;
    0.68
     accomplishing
    0.62
     communicate
    0.60
     censi
    0.60
     measuring
    0.58
    isseurs
    0.57
     measure
    0.57
     useDispatch
    0.57
     detect
    0.57
    Activations Density 0.569%

    No Known Activations