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. 10294
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical research and specific illnesses

    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
     WAG
    -1.09
     MG
    -1.08
     NG
    -1.08
     NAG
    -1.07
     Hog
    -1.06
     ng
    -1.06
    ANG
    -1.06
    mg
    -1.05
     Pog
    -1.05
     Tig
    -1.05
    POSITIVE LOGITS
     GV
    0.54
    RenderAtEndOf
    0.54
     GK
    0.51
     GP
    0.49
     GW
    0.49
     GC
    0.47
    ($__
    0.47
     GF
    0.45
     CWE
    0.42
    endwhile
    0.42
    Activations Density 4.028%

    No Known Activations