© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 128728
    Prev
    Next
    INDEX
    Explanations

    occurrences of object-related terms or keywords in a programming context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    obj object names

    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
    Negative Logits
     ब्रेकडाउन
    -0.65
    Viitteet
    -0.61
    󠁮
    -0.60
     незавершена
    -0.59
    currentColor
    -0.56
     WaitForSeconds
    -0.56
    canActivate
    -0.54
    󠁣
    -0.54
    dine
    -0.54
    KURZBESCHREIBUNG
    -0.54
    POSITIVE LOGITS
    Obj
    2.08
    obj
    1.62
     Obj
    1.57
    OBJ
    1.25
    objs
    1.14
     OBJ
    1.11
     Objek
    1.10
     obj
    1.09
     objs
    1.00
    Objs
    0.99
    Activations Density 0.013%

    No Known Activations