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. 2139
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions

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

    LaTeX math mode: dollar signs and circumflexes

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and scientific units

    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
     Италијани
    -0.59
    Bearer
    -0.50
     пола
    -0.50
    OMAS
    -0.50
    ErrorType
    -0.48
     just
    -0.48
     manj
    -0.47
    Abitanti
    -0.47
    preise
    -0.47
    boden
    -0.46
    POSITIVE LOGITS
     виправивши
    0.92
     '\\;'
    0.86
     bezeichneter
    0.84
    HtmlAttribute
    0.80
    ModelAdmin
    0.76
    IntoConstraints
    0.74
     DialogInterface
    0.74
    ⓧ
    0.71
    XmlAccessType
    0.69
    apunov
    0.68
    Activations Density 0.226%

    No Known Activations