© 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. 24-GEMMASCOPE-RES-16K
    11. 6434
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding or comprehension

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

    "understand" or its variations

    np_acts-logits-general · gemini-2.0-flash

    understanding, comprehension, or lack thereof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     epics
    -0.44
    latLng
    -0.40
     rpc
    -0.40
     Poultry
    -0.39
    Rpc
    -0.38
     bibli
    -0.38
     seny
    -0.37
     ephe
    -0.37
     epic
    -0.36
     Rolling
    -0.36
    POSITIVE LOGITS
     Understanding
    1.09
     understand
    1.08
     understanding
    1.06
     Understand
    1.05
    Understanding
    1.03
    understand
    1.02
    understanding
    1.01
     understands
    1.01
    Understand
    0.98
     understood
    0.81
    Activations Density 0.081%

    No Known Activations