© 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. 3182
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their properties related to equations

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

    grammatical markers like "to", "is", "in", and other auxiliary verbs that help describe actions or states.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    verbs that indicate a state or condition that exists in a particular way or circumstance.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     kuitenkin
    -0.39
     Sosial
    -0.38
     Keuangan
    -0.36
    República
    -0.35
     bowiem
    -0.35
     humanidade
    -0.34
     Budaya
    -0.33
     Versammlung
    -0.32
     käytt
    -0.32
     extré
    -0.32
    POSITIVE LOGITS
    tagHelperRunner
    0.90
     FetchType
    0.89
    rungsseite
    0.83
    QMetaType
    0.77
     Normdatei
    0.75
     يتيمه
    0.73
    MLLoader
    0.72
    OGND
    0.72
    IVEREF
    0.71
    IntoConstraints
    0.70
    Activations Density 0.632%

    No Known Activations