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. 7-GEMMASCOPE-RES-16K
    6. 6244
    Prev
    Next
    INDEX
    Explanations

    various numerical and symbolic representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }-${
    -0.53
     Sí
    -0.53
     мәкал
    -0.53
     délic
    -0.53
    enumii
    -0.52
     Chia
    -0.52
    قه
    -0.51
    olester
    -0.51
    pij
    -0.50
     nematodes
    -0.50
    POSITIVE LOGITS
    WritableDatabase
    0.88
    endphp
    0.83
     kasarigan
    0.82
     الرياضيه
    0.81
    ệc
    0.63
    AntiForgeryToken
    0.62
     LCCN
    0.59
    Джерела
    0.58
    AnimationsModule
    0.57
     BoxFit
    0.57
    Activations Density 0.020%

    No Known Activations