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. 0-GEMMASCOPE-RES-16K
    6. 7811
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "zip."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.79
     المعيارى
    -0.74
    /**
    -0.70
    RTHOOK
    -0.68
    Искәрмәләр
    -0.67
     насељу
    -0.67
    Билгалдахарш
    -0.66
    complexType
    -0.64
    \{\\
    -0.64
    ContentAlignment
    -0.64
    POSITIVE LOGITS
     pumpkin
    0.81
    Pumpkin
    0.75
     Pumpkin
    0.73
     turbo
    0.66
     Turbo
    0.63
    Turbo
    0.63
     GPS
    0.63
    pharmacy
    0.61
    GPS
    0.60
    Jonathan
    0.60
    Activations Density 0.073%

    No Known Activations