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. 10088
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate permission or capability

    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
    YNC
    -0.83
     StatelessWidget
    -0.80
    numerusform
    -0.79
    SessionFactory
    -0.77
     بيها
    -0.75
     Eighth
    -0.74
     Ceinture
    -0.73
     Arxivat
    -0.73
     famí
    -0.73
    pyx
    -0.72
    POSITIVE LOGITS
     ALLOW
    1.87
    ALLOW
    1.81
     Allow
    1.80
     allow
    1.79
     allows
    1.72
     allowed
    1.67
     Allows
    1.66
    Allow
    1.64
     allowing
    1.63
    allow
    1.60
    Activations Density 0.081%

    No Known Activations