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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 8619
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values and their relevance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     publiques
    -0.50
    決
    -0.43
     chercher
    -0.41
    etat
    -0.41
     sportivo
    -0.40
     déclar
    -0.40
     moment
    -0.39
     nemen
    -0.38
     specchio
    -0.37
    ,
    -0.37
    POSITIVE LOGITS
    StoryboardSegue
    0.95
     raiſ
    0.80
     Normdatei
    0.79
     nahilalakip
    0.74
     Waray
    0.71
     تضيفلها
    0.71
     فريبيس
    0.70
    ReusableCell
    0.70
    DOCTYPE
    0.69
    setDo
    0.68
    Activations Density 0.046%

    No Known Activations