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. 2856
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to innovation, sustainability, and social equity

    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
     كومونز
    -0.83
    RenderAtEndOf
    -0.79
    tonode
    -0.76
    SequentialGroup
    -0.69
    DoubleQuotes
    -0.68
    TagMode
    -0.65
     >=",
    -0.62
     Мексичка
    -0.60
    URLException
    -0.59
    complexContent
    -0.59
    POSITIVE LOGITS
    ulemon
    0.48
     atmosphere
    0.47
     förb
    0.46
    hdys
    0.44
     férias
    0.44
     מוש
    0.44
    est
    0.44
    NewGuid
    0.43
     lunches
    0.43
    Localisation
    0.43
    Activations Density 1.089%

    No Known Activations