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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11754
    Prev
    Next
    INDEX
    Explanations

    special formatting and annotations in structured text or code

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

    Follows punctuation or section delimiters

    np_acts-logits-general · gemini-2.0-flash

    section separators and numbering

    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
    riwal
    -0.79
    IUrlHelper
    -0.79
    databind
    -0.76
     oprot
    -0.76
    banez
    -0.71
    djangoproject
    -0.71
    iStock
    -0.71
    InvalidProtocol
    -0.70
     AspNetCore
    -0.69
    }{*}{
    -0.69
    POSITIVE LOGITS
    .........
    1.08
    !!!!!
    0.91
    ?????
    0.86
     enfans
    0.83
    ooooo
    0.82
    !!!!
    0.80
    AAA
    0.80
    xxxxx
    0.80
     tenuta
    0.78
     religieuses
    0.77
    Activations Density 0.283%

    No Known Activations