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. 10273
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals, particularly in a professional context

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

    Tokens preceding quoted statements or comments

    np_acts-logits-general · gemini-2.0-flash

    statements by officials

    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
    出版年
    -0.60
     vPvB
    -0.58
    ReusableCell
    -0.53
     allegation
    -0.52
    ^(@)
    -0.52
     accuse
    -0.50
     unwritten
    -0.50
     насељу
    -0.50
    ActionTypes
    -0.49
     liệu
    -0.48
    POSITIVE LOGITS
     commented
    1.31
    Commenting
    1.12
     commenting
    1.08
     comments
    1.05
     said
    1.00
     commento
    0.98
     comment
    0.98
    commented
    0.97
     Comment
    0.95
     comenta
    0.89
    Activations Density 0.086%

    No Known Activations