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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1774
    Prev
    Next
    INDEX
    Explanations

    elements that represent structured data or programming constructs

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

    Code snippets with brackets and plus signs

    np_acts-logits-general · gemini-2.0-flash

    code snippets with plus/quotes

    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
     Процитовано
    -0.79
    Datuak
    -0.74
    MENAFN
    -0.70
     <<
    -0.69
    новништво
    -0.69
    '],$
    -0.68
    ={()=>
    -0.68
    🏼
    -0.67
    Atsauces
    -0.65
     @(
    -0.65
    POSITIVE LOGITS
    SharedCtor
    0.51
     متعلقه
    0.48
    část
    0.47
    ㎡
    0.45
    --
    0.44
     appelez
    0.44
    antMatchers
    0.42
    发表于
    0.42
    —
    0.40
    hess
    0.40
    Activations Density 0.455%

    No Known Activations