Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 26
    Prev
    Next
    INDEX
    Explanations

    _dates and numerical references within the document_

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

    Dates with the day "1"

    np_acts-logits-general · gemini-2.0-flash

    dates in July

    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
     pinulongan
    -1.06
    IsContent
    -0.99
     <=",
    -0.94
    contentLoaded
    -0.90
    +#+#
    -0.84
     himo
    -0.81
    #+#
    -0.80
    ItemBackground
    -0.80
     CreateTagHelper
    -0.79
     ***!
    -0.78
    POSITIVE LOGITS
    INTA
    0.49
     baja
    0.48
    اص
    0.46
     слу
    0.45
    기에
    0.44
    ixe
    0.44
    eret
    0.43
    lecteur
    0.43
     paid
    0.43
     pí
    0.43
    Activations Density 0.199%

    No Known Activations