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. 16-GEMMASCOPE-RES-16K
    6. 12174
    Prev
    Next
    INDEX
    Explanations

    coding constructs and programming syntax

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

    Numbers followed by exponents

    np_acts-logits-general · gemini-2.0-flash

    numbers and special characters like ***

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.73
    DockStyle
    -0.72
    참고
    -0.70
     الحره
    -0.70
    ChildScrollView
    -0.63
    깥
    -0.61
     éducation
    -0.60
     تانيه
    -0.60
     CrossRef
    -0.60
     kasarigan
    -0.60
    POSITIVE LOGITS
    évaluateur
    0.55
    <bos>
    0.52
     distance
    0.50
    下载附件
    0.49
    Namara
    0.46
    hotra
    0.46
    #+#
    0.45
    yorsunuz
    0.45
    nocześnie
    0.45
     nă
    0.45
    Activations Density 0.175%

    No Known Activations