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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15172
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases that indicate significance or emphasis in a text

    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
     sufficiently
    -0.97
     enough
    -0.84
     Enough
    -0.81
     suficientemente
    -0.81
     abbastanza
    -0.80
     genoeg
    -0.79
     suffisamment
    -0.77
     sufficient
    -0.73
     ENOUGH
    -0.72
     suficientes
    -0.70
    POSITIVE LOGITS
     насељу
    0.72
    UnusedPrivate
    0.65
    المشاركات
    0.64
    archiviato
    0.62
     MessageBoxIcon
    0.61
    ztály
    0.61
    IntoConstraints
    0.61
    ValueGeneration
    0.61
    getItemId
    0.59
     actionMode
    0.57
    Activations Density 0.663%

    No Known Activations