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. 20-GEMMASCOPE-RES-16K
    6. 4913
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to obligations and responsibilities in court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a modal verb

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     letting
    -0.75
     sticking
    -0.75
     ruining
    -0.71
     hooked
    -0.70
     popping
    -0.70
     Putting
    -0.69
     sneaking
    -0.69
     tweaking
    -0.68
     messing
    -0.68
     putting
    -0.67
    POSITIVE LOGITS
     pinulongan
    0.71
     poffe
    0.71
     raiſ
    0.65
    errHandler
    0.65
     obſ
    0.65
     successivamente
    0.64
     مشارکت‌کنندگان
    0.64
     Vikipedi
    0.63
     defire
    0.62
     caufe
    0.62
    Activations Density 1.247%

    No Known Activations