© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2804
    Prev
    Next
    INDEX
    Explanations

    structural elements and classifications in research studies

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

    "Materials and Methods" section

    np_acts-logits-general · gemini-2.0-flash

    Materials and Methods sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.52
    IonicModule
    -0.51
    Aiheesta
    -0.46
    homonymie
    -0.43
    ReusableCell
    -0.40
     onOptions
    -0.40
    ChildScrollView
    -0.39
    jsonwebtoken
    -0.39
    Jîn
    -0.39
    grao
    -0.38
    POSITIVE LOGITS
     undertook
    0.55
     undertaken
    0.51
     conducted
    0.47
     Conducted
    0.45
    conducted
    0.45
     methodology
    0.43
     Carried
    0.41
    intervento
    0.41
     carried
    0.40
    Methodology
    0.40
    Activations Density 1.810%

    No Known Activations