© 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. 30-GEMMASCOPE-RES-16K
    11. 15095
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to patterns and deficiencies

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

    Preceding certain words

    np_acts-logits-general · gemini-2.0-flash

    energy and energies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poursuite
    -0.38
     hinweg
    -0.36
     boot
    -0.35
     Anis
    -0.35
    Weiterlesen
    -0.35
    醐
    -0.35
    ódromo
    -0.35
    ciler
    -0.35
    nasium
    -0.35
     oignons
    -0.34
    POSITIVE LOGITS
     energy
    1.20
     energies
    1.02
    energy
    1.02
     energía
    0.96
     ENERGY
    0.94
     energia
    0.94
     énergie
    0.93
     energie
    0.92
     Energie
    0.88
    énergie
    0.88
    Activations Density 0.177%

    No Known Activations