© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8763
    Prev
    Next
    INDEX
    Explanations

    emotional expressions of struggle and resilience

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

    Adverbs of frequency

    np_acts-logits-general · gemini-2.0-flash

    frequency and regularity

    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
     finalmente
    -0.52
     ponownie
    -0.48
    reszcie
    -0.47
     finally
    -0.44
     erstmals
    -0.43
     opět
    -0.42
     наконец
    -0.41
     znovu
    -0.41
     Finalmente
    -0.41
    getMenuInflater
    -0.41
    POSITIVE LOGITS
     regularly
    0.97
     frequently
    0.90
     routinely
    0.82
     frequent
    0.79
     whenever
    0.79
    frequently
    0.77
     occasionally
    0.77
    Occasionally
    0.77
     often
    0.76
    经常
    0.76
    Activations Density 0.483%

    No Known Activations