© 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. 2956
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and structures related to systems or equations

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

    LaTeX or code snippets

    np_acts-logits-general · gemini-2.0-flash

    Samuels, bio, config

    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
    printStackTrace
    -0.45
     مشين
    -0.40
     ané
    -0.39
     eh
    -0.38
     Anh
    -0.38
    meanor
    -0.38
    艋
    -0.37
     convite
    -0.36
    出版年
    -0.36
     aço
    -0.36
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.88
    новништво
    0.56
    principalColumn
    0.54
    ⓧ
    0.49
     betweenstory
    0.48
     ProtoMessage
    0.44
     invokingState
    0.43
     يتيمه
    0.40
     skates
    0.36
    Skocz
    0.36
    Activations Density 1.200%

    No Known Activations