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. 21-GEMMASCOPE-RES-16K
    6. 6604
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structures related to algebra and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     her
    -0.40
    Diction
    -0.40
    kebox
    -0.37
     mình
    -0.37
     Docs
    -0.36
    gnings
    -0.36
     be
    -0.35
     Dive
    -0.35
     Ở
    -0.35
    her
    -0.34
    POSITIVE LOGITS
    ftagPool
    0.93
     الرياضيه
    0.88
     typelib
    0.88
    RectangleBorder
    0.84
     дописавши
    0.83
    EndContext
    0.83
     vPvB
    0.81
    basicConfig
    0.79
     '\\;'
    0.76
    httphttps
    0.75
    Activations Density 0.479%

    No Known Activations