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. 11760
    Prev
    Next
    INDEX
    Explanations

    keywords related to code structure, particularly public methods and their parameters

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

    Code, especially parameters or configurations

    np_acts-logits-general · gemini-2.0-flash

    String type declarations

    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
     mass
    -0.46
     an
    -0.45
    nummer
    -0.44
    iore
    -0.43
    ه‌
    -0.43
     liệu
    -0.43
    list
    -0.43
    编号
    -0.43
    OMEM
    -0.42
    yle
    -0.42
    POSITIVE LOGITS
     String
    1.30
    String
    1.28
     resourceCulture
    1.02
    AxisAlignment
    0.97
    NSString
    0.94
     tartalomajánló
    0.91
    ंदीखरीदारी
    0.90
    sidemargin
    0.88
     виправивши
    0.87
     مشين
    0.87
    Activations Density 0.064%

    No Known Activations