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. 254
    Prev
    Next
    INDEX
    Explanations

    references to binary data sizes and types

    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
    DockStyle
    -0.58
    DeleteBehavior
    -0.53
     Thinking
    -0.51
     courtesy
    -0.51
     empre
    -0.50
    principalTable
    -0.49
     basi
    -0.49
    Teles
    -0.48
    edere
    -0.48
    ViewStyle
    -0.48
    POSITIVE LOGITS
     bits
    0.99
     Bit
    0.88
     bit
    0.85
     Bits
    0.77
    Bit
    0.75
    LEncoder
    0.72
     BITS
    0.70
    bited
    0.66
    INSTANCE
    0.65
    odeon
    0.64
    Activations Density 0.121%

    No Known Activations