© 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. 16-GEMMASCOPE-RES-16K
    11. 10983
    Prev
    Next
    INDEX
    Explanations

    references to literary works or discussions about the structure and function of language

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

    German, Norwegian/older version, or code-related text

    np_acts-logits-general · gemini-2.0-flash

    installation status

    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
    enumii
    -0.71
    __(/*!
    -0.65
    ക്ഷ
    -0.58
     agitation
    -0.57
     ciga
    -0.56
     buc
    -0.53
    ונות
    -0.52
     redundancy
    -0.51
     Mino
    -0.50
     sensitization
    -0.50
    POSITIVE LOGITS
     is
    0.63
     estimés
    0.59
     do
    0.57
    
    0.55
     does
    0.53
     дописавши
    0.52
     initComponents
    0.52
    "]);
    0.52
    Šaltiniai
    0.50
    wirt
    0.49
    Activations Density 0.045%

    No Known Activations