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. 24-GEMMASCOPE-RES-16K
    6. 8199
    Prev
    Next
    INDEX
    Explanations

    references to URL handling and sanitization in code

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

    Code, error messages, and numbers

    np_acts-logits-general · gemini-2.0-flash

    ocrystals, 0 iterations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }^{[
    -0.61
    reactstrap
    -0.60
     referenties
    -0.58
    ⓧ
    -0.58
    getMenuInflater
    -0.56
    Seven
    -0.56
    more
    -0.56
    imdi
    -0.56
     seven
    -0.55
    vikle
    -0.54
    POSITIVE LOGITS
    	
    0.96
    Personensuche
    0.56
    fromnode
    0.54
     abstracted
    0.50
    DIPSETTING
    0.48
     AssemblyTitle
    0.46
     abstraction
    0.44
    HtmlAttribute
    0.43
    hésite
    0.43
    Nazionale
    0.42
    Activations Density 0.014%

    No Known Activations