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. 12-GEMMASCOPE-RES-16K
    6. 9502
    Prev
    Next
    INDEX
    Explanations

    specific terms related to legal or formal documentation, particularly those involving agreements or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.66
    NOPQRST
    -0.60
    artige
    -0.59
     Efq
    -0.58
    ChildScrollView
    -0.56
    QUET
    -0.55
     Portail
    -0.54
    CancelButton
    -0.54
    mejores
    -0.53
    setVerticalGroup
    -0.53
    POSITIVE LOGITS
    StoreMessageInfo
    0.69
     estekak
    0.67
    RTEX
    0.63
     astore
    0.55
    enumi
    0.51
     चीज़ों
    0.51
     nakalista
    0.51
    AccessorTable
    0.50
    +#+#
    0.50
     väli
    0.49
    Activations Density 0.472%

    No Known Activations