© 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. 6190
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or principal aspects of a subject

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

    phrases that begin with "one of the" or use "one of" to set up a descriptive statement.

    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
    richTextPanel
    -0.63
    transQ
    -0.59
     Roskov
    -0.55
     useRouter
    -0.52
    jsxFileName
    -0.50
     useAuth
    -0.48
     Cardinale
    -0.47
    raulic
    -0.47
    XmlAccessorType
    -0.47
    󠁮
    -0.47
    POSITIVE LOGITS
    Among
    0.44
     Among
    0.42
     independencia
    0.41
     notamment
    0.40
    Vanjske
    0.39
     notable
    0.38
     parmi
    0.38
    VersionUID
    0.37
    Среди
    0.37
     contributory
    0.36
    Activations Density 0.275%

    No Known Activations