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. 4122
    Prev
    Next
    INDEX
    Explanations

    references to legal obligations and financial responsibilities

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

    following "shall" or related to legal/formal requirements

    np_acts-logits-general · gemini-2.0-flash

    shall obligations

    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
    Yesterday
    -0.62
     yesterday
    -0.61
    IUrlHelper
    -0.58
     fler
    -0.57
    ⓘ
    -0.57
     hoping
    -0.56
     Yesterday
    -0.56
    はじめに
    -0.55
    Almost
    -0.54
    zyden
    -0.54
    POSITIVE LOGITS
     shall
    1.09
    shall
    0.96
     Shall
    0.84
     forthwith
    0.79
     fhall
    0.74
     SHALL
    0.73
    Shall
    0.72
     Appropriate
    0.69
     appropriate
    0.69
     promptly
    0.68
    Activations Density 0.511%

    No Known Activations