© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4323
    Prev
    Next
    INDEX
    Explanations

    words associated with ownership and security

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

    action-oriented phrases describing capability or potential.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    SourceChecksum
    -0.68
    RegressionTest
    -0.66
     otomatig
    -0.66
    Rüyada
    -0.65
     queſta
    -0.64
    帖最后由
    -0.63
     للاسماء
    -0.63
     Normdatei
    -0.61
     referrerpolicy
    -0.60
    enumi
    -0.60
    POSITIVE LOGITS
     ihtiyac
    0.39
    entuh
    0.31
     Komunikasi
    0.30
    def
    0.30
    direkt
    0.28
     поддержа
    0.27
    Def
    0.26
     Bidang
    0.26
    DEF
    0.25
     langsung
    0.25
    Activations Density 0.378%

    No Known Activations