© 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. 33-GEMMASCOPE-RES-16K
    6. 10678
    Prev
    Next
    INDEX
    Explanations

    quantities and references to "some" in various contexts, often addressing inclusivity or vagueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    łość
    -0.41
     sociali
    -0.35
    WithIdentifier
    -0.35
    zeit
    -0.34
     today
    -0.34
    shadowRadius
    -0.34
    டன்
    -0.34
     digress
    -0.33
    ぞ
    -0.33
    itemBuilder
    -0.33
    POSITIVE LOGITS
     respects
    1.01
     sense
    1.01
     regard
    0.98
     regards
    0.97
     sentido
    0.93
     sentidos
    0.86
     way
    0.85
     respect
    0.84
     instance
    0.83
     instances
    0.81
    Activations Density 0.430%

    No Known Activations