Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15523
    Prev
    Next
    INDEX
    Explanations

    states of emotional awareness and complex internal experiences.

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

    technical information related to programming and software development.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    misspelled or unconventionally spelled words, particularly those with common spelling errors or alternative spellings.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    with uncommon suffixes

    np_acts-logits-general · gemini-2.0-flash

    word endings

    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
    CodeDom
    -0.55
    TestTools
    -0.54
    doGet
    -0.53
    akuan
    -0.53
    stdc
    -0.53
     ◄
    -0.52
    Viitteet
    -0.51
     dima
    -0.51
     Dauer
    -0.51
     AnyObject
    -0.50
    POSITIVE LOGITS
     للمعارف
    1.04
     تانيه
    0.76
    RegistryLite
    0.76
    
    0.75
    CodeAttribute
    0.74
    حياته
    0.71
    省市镇
    0.70
    InjectAttribute
    0.70
    HideFlags
    0.69
    ̣i
    0.67
    Activations Density 0.543%

    No Known Activations