© 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. 22-GEMMASCOPE-RES-16K
    11. 5418
    Prev
    Next
    INDEX
    Explanations

    references to organizations or entities, particularly in a formal or business context

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

    following commas, parentheses, or dashes

    np_acts-logits-general · gemini-2.0-flash

    formerly known as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    例えば
    -0.56
    たとえば
    -0.52
    theless
    -0.52
    initions
    -0.48
    出版年
    -0.47
    ंत्री
    -0.46
    比如说
    -0.46
    বার
    -0.45
     старости
    -0.45
     Misalnya
    -0.44
    POSITIVE LOGITS
     formerly
    1.14
    formerly
    1.10
     aka
    1.01
     known
    0.99
    known
    0.93
    itself
    0.90
    aka
    0.89
     Formerly
    0.89
     located
    0.88
     onderdeel
    0.86
    Activations Density 0.623%

    No Known Activations