© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81674
    Prev
    Next
    INDEX
    Explanations

    words related to chemical processes or conditions

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

    words ending in ination

    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
     jButton
    -0.48
     المعيارى
    -0.46
    ztály
    -0.46
    Buddy
    -0.43
    JButton
    -0.43
    Trial
    -0.42
     forceps
    -0.42
    '&:
    -0.41
    cpu
    -0.41
    erapeu
    -0.40
    POSITIVE LOGITS
    ination
    1.93
    INATION
    1.38
    inate
    1.34
    inated
    1.21
    inat
    1.07
    inar
    1.05
    inator
    0.96
    minate
    0.93
    inary
    0.93
    mination
    0.92
    Activations Density 0.022%

    No Known Activations