© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1639
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one" and related phrases indicating singularity or singular references

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

    the word "one" in various contexts.

    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
     desplaz
    -0.50
     cuisson
    -0.49
     fazenda
    -0.47
     régal
    -0.47
    zzleHttp
    -0.46
    ecimento
    -0.45
    chengladbach
    -0.44
     caminhada
    -0.44
    dbach
    -0.44
    wußt
    -0.43
    POSITIVE LOGITS
     ONE
    1.16
     one
    1.16
     One
    1.08
    One
    1.06
    one
    0.93
    HasOne
    0.83
    findOne
    0.83
    getOne
    0.83
    ONE
    0.82
     findOne
    0.81
    Activations Density 0.166%

    No Known Activations