© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13088
    Prev
    Next
    INDEX
    Explanations

    questions related to career choices and education pathways for young individuals

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

    Follows punctuation or parentheses

    np_acts-logits-general · gemini-2.0-flash

    technical specifications and multilingual content

    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
    atiz
    -0.53
    ondale
    -0.47
    CLOSE
    -0.47
    INTER
    -0.46
    マキ
    -0.45
    성
    -0.45
    Operands
    -0.44
    MANY
    -0.44
    agrad
    -0.44
     De
    -0.43
    POSITIVE LOGITS
    HasForeignKey
    0.93
    (!__
    0.90
    帖最后由
    0.87
    новниш
    0.86
     تضيفلها
    0.86
     autorytatywna
    0.83
    findpost
    0.83
    TagMode
    0.79
    存于互联网档案馆
    0.79
    Revenir
    0.79
    Activations Density 0.274%

    No Known Activations