© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 84918
    Prev
    Next
    INDEX
    Explanations

    terms related to specific scientific or technical concepts, particularly in the fields of biology and physics

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

    Gaster, neurotransmitters, cirrhosis

    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
    VIAF
    -0.54
    enfone
    -0.52
    athione
    -0.51
     Kail
    -0.50
     snippetHide
    -0.49
    #+#
    -0.48
    DrawerToggle
    -0.47
    WindowConstants
    -0.47
    UrlResolution
    -0.47
     <=",
    -0.47
    POSITIVE LOGITS
    丁目
    0.43
    WithMany
    0.43
    ogaster
    0.42
    Unread
    0.41
    hilangan
    0.40
    CompoundButton
    0.39
    glLoad
    0.38
    illium
    0.38
    Appender
    0.37
    GLuint
    0.36
    Activations Density 0.055%

    No Known Activations