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. 6-GEMMASCOPE-RES-16K
    6. 13389
    Prev
    Next
    INDEX
    Explanations

    elements of code related to function definitions and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     通販
    -0.77
    NUMX
    -0.73
    ftagPool
    -0.71
     snippetHide
    -0.68
    Huile
    -0.68
    ReusableCell
    -0.67
    ="@+
    -0.66
    ArrowToggle
    -0.64
    Rhestr
    -0.63
    DMETHOD
    -0.61
    POSITIVE LOGITS
    <bos>
    0.55
     complete
    0.46
    }{
    0.46
    																
    0.46
    WithIOException
    0.45
    شوند
    0.45
    es
    0.45
    )
    0.44
     supposing
    0.44
     particolari
    0.44
    Activations Density 0.138%

    No Known Activations