© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7137
    Prev
    Next
    INDEX
    Explanations

    structural elements in coding or programming contexts, particularly related to definitions and protocols

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

    Code snippets or hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    SQL keyword select

    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
     nahilalakip
    -0.54
    UserScript
    -0.48
     henvisninger
    -0.47
     cristianismo
    -0.46
    Geplaatst
    -0.46
    principalColumn
    -0.44
     defaultstate
    -0.43
     secundario
    -0.41
     Komunikasi
    -0.41
     Bidang
    -0.41
    POSITIVE LOGITS
    outine
    0.50
     KeyError
    0.46
    屓
    0.45
    cif
    0.45
    mpotent
    0.43
    sior
    0.43
    yntax
    0.43
     procrastin
    0.43
     endforeach
    0.42
    bory
    0.42
    Activations Density 0.666%

    No Known Activations