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. 5-GEMMASCOPE-RES-16K
    6. 16338
    Prev
    Next
    INDEX
    Explanations

    assignment statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conversation
    -0.67
    юрпри
    -0.61
    dis
    -0.61
    丁
    -0.57
     μή
    -0.56
    lis
    -0.55
     Schild
    -0.55
     Heim
    -0.55
     Ohr
    -0.55
    ations
    -0.55
    POSITIVE LOGITS
     =>
    2.07
    =>
    1.74
    )=>
    1.45
    "=>
    1.39
     =>
    
    1.30
    '=>
    1.21
    =>"
    1.20
     ⇒
    1.18
     =>'
    1.16
    =>$
    1.16
    Activations Density 0.024%

    No Known Activations