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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 19928
    Prev
    Next
    INDEX
    Explanations

    references to anatomical structures and surgical procedures related to the brain

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

    temporal lobe, dementia, bone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.41
     оригіналу
    -0.38
    PyExc
    -0.35
     Jha
    -0.34
     cast
    -0.33
     ies
    -0.33
     Curran
    -0.33
    beforeSend
    -0.33
    $("#
    -0.32
    metadata
    -0.32
    POSITIVE LOGITS
    thâu
    0.62
    ########.
    0.59
    +#+#
    0.59
     незавершена
    0.56
    httphttps
    0.53
    ativement
    0.53
    Rohy
    0.52
    Personendaten
    0.52
    twimg
    0.51
    richTextPanel
    0.51
    Activations Density 0.034%

    No Known Activations