© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5515
    Prev
    Next
    INDEX
    Explanations

    various object identifiers in code-related contexts

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

    Code referring to an object named "obj"

    np_acts-logits-general · gemini-2.0-flash

    object type checks

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    enzie
    -0.58
    Bibliograf
    -0.55
    inspace
    -0.54
    ection
    -0.54
     Reichen
    -0.53
    ObjectModel
    -0.52
    ation
    -0.52
     }}}{
    -0.52
     constitución
    -0.50
    TemporalType
    -0.50
    POSITIVE LOGITS
     ctx
    0.80
    ctx
    0.80
    Obj
    0.76
    obj
    0.75
     obj
    0.74
     arr
    0.70
    Ctx
    0.68
     cmd
    0.67
    setMsg
    0.64
    Msg
    0.63
    Activations Density 0.235%

    No Known Activations