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

    Neuronpedia

    APICircuit 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. 15-GEMMASCOPE-RES-16K
    6. 2422
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and values related to energy and particle physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.62
    ↵↵↵
    -0.57
     The
    -0.55
     for
    -0.54
    iche
    -0.50
     by
    -0.47
    ospor
    -0.47
     made
    -0.47
     be
    -0.47
     who
    -0.46
    POSITIVE LOGITS
     Normdatei
    0.77
    reszcie
    0.69
     Majefty
    0.68
    ArgsConstructor
    0.68
     Efq
    0.67
     fevere
    0.67
    adpleegd
    0.67
     Shakspeare
    0.66
     MainAxisSize
    0.66
     iſt
    0.65
    Activations Density 1.397%

    No Known Activations