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. 3958
    Prev
    Next
    INDEX
    Explanations

    references to specific thresholds and limits

    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
     bianche
    -0.65
     déchir
    -0.65
    rceil
    -0.64
     perpetuity
    -0.63
     émissions
    -0.62
     séjours
    -0.61
     rembourse
    -0.60
     pouvoirs
    -0.60
     piety
    -0.60
     hábito
    -0.60
    POSITIVE LOGITS
     certain
    1.20
     Certain
    0.97
     certaine
    0.94
    certain
    0.88
    Certain
    0.85
     specific
    0.82
     cierta
    0.79
     bestimmte
    0.79
     CERTAIN
    0.77
     particular
    0.77
    Activations Density 0.356%

    No Known Activations