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. 25-GEMMASCOPE-RES-16K
    6. 10433
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership and liability in web content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    h
    -1.03
    st
    -1.03
    re
    -1.02
    z
    -0.97
    as
    -0.96
    in
    -0.96
    v
    -0.94
    at
    -0.94
    se
    -0.94
    c
    -0.92
    POSITIVE LOGITS
    findpost
    0.96
     Biôgrafia
    0.95
    webElementXpaths
    0.93
    GEBURTSDATUM
    0.84
     témoig
    0.78
    sizeCache
    0.78
     geſch
    0.77
     dieſe
    0.77
     imagui
    0.77
    <unused98>
    0.76
    Activations Density 0.663%

    No Known Activations