© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4016
    Prev
    Next
    INDEX
    Explanations

    references to components in scientific and industrial contexts

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

    Text after parentheses or numbers

    np_acts-logits-general · gemini-2.0-flash

    exhibition shows

    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
     <>",
    -0.49
     CanadaChoose
    -0.48
    省市镇
    -0.43
    httphttps
    -0.42
     Référence
    -0.41
    adaptiveStyles
    -0.40
     mijne
    -0.40
     moeite
    -0.40
    DIPSETTING
    -0.39
    apprendre
    -0.39
    POSITIVE LOGITS
    ngdoc
    0.48
    Cá
    0.46
    名
    0.45
     hood
    0.42
     ſche
    0.42
     bezeichneter
    0.41
     PLACE
    0.41
     heel
    0.41
     Roskov
    0.40
    顧
    0.39
    Activations Density 1.353%

    No Known Activations