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. 12-GEMMASCOPE-RES-16K
    6. 6393
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.67
    fjspx
    -0.66
     AssemblyCulture
    -0.64
    ReusableCell
    -0.62
    новништво
    -0.62
    ⓧ
    -0.62
    abestanden
    -0.62
     незавершена
    -0.58
     متعلقه
    -0.58
    oa̍t
    -0.57
    POSITIVE LOGITS
     oog
    0.55
    UseVisualStyle
    0.51
    ugu
    0.50
    corresponding
    0.48
    Namara
    0.48
    épend
    0.47
    endphp
    0.47
    ByteString
    0.46
     nourrir
    0.46
    Shutterstock
    0.45
    Activations Density 0.775%

    No Known Activations