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. 15-GEMMASCOPE-RES-16K
    6. 4266
    Prev
    Next
    INDEX
    Explanations

    function calls and their associated parameters

    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
    ↵↵
    -0.56
     can
    -0.52
     in
    -0.50
     h
    -0.50
     D
    -0.50
    g
    -0.49
     (
    -0.49
     The
    -0.48
    h
    -0.47
     too
    -0.47
    POSITIVE LOGITS
     متعلقه
    1.33
     myſelf
    1.22
     للمعارف
    1.19
    تقاوى
    1.14
     reaſon
    1.13
     poffible
    1.12
     Houſe
    1.11
     purpoſe
    1.11
     Monfieur
    1.10
    Хьажоргаш
    1.09
    Activations Density 0.324%

    No Known Activations