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. 22-GEMMASCOPE-RES-16K
    6. 10388
    Prev
    Next
    INDEX
    Explanations

    symbols and notations related to mathematical expressions, particularly in linear algebra and combinatorics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or logical expressions

    np_acts-logits-general · gemini-2.0-flash

    indices and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.59
    makeText
    -0.55
    uzz
    -0.50
     doGet
    -0.49
    getDoctrine
    -0.49
    ReturnType
    -0.48
    InputBorder
    -0.47
    abestanden
    -0.46
    BASEPATH
    -0.46
    󠁢
    -0.46
    POSITIVE LOGITS
    j
    0.96
     i
    0.96
     j
    0.91
    i
    0.87
     k
    0.74
    k
    0.74
     ith
    0.67
    j
    0.63
    𝑗
    0.63
    BagConstraints
    0.63
    Activations Density 1.942%

    No Known Activations