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. 17-GEMMASCOPE-RES-16K
    6. 11370
    Prev
    Next
    INDEX
    Explanations

    function calls and error handling related to CUDA devices and their initialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TintMode
    -0.49
    ::~
    -0.48
    ("")]
    
    -0.47
    textTheme
    -0.43
    fres
    -0.43
    OGND
    -0.42
     so
    -0.41
    )|^{
    -0.40
    velop
    -0.39
    GetEnumerator
    -0.38
    POSITIVE LOGITS
     ddelweddau
    0.91
    HtmlAttribute
    0.70
     <=",
    0.68
     Infórmanos
    0.67
    новништво
    0.67
    ctory
    0.67
    حوالہ
    0.66
     Мексичка
    0.66
     giuri
    0.66
     שוליים
    0.66
    Activations Density 0.803%

    No Known Activations