© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5578
    Prev
    Next
    INDEX
    Explanations

    structures and syntax related to generic programming and class definitions

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

    Code/pointers related to objects

    np_acts-logits-general · gemini-2.0-flash

    object, entity, pointer, literal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getItemId
    -0.40
    AndEndTag
    -0.39
    uete
    -0.38
    DrawerToggle
    -0.38
     Paglinawan
    -0.36
    LookAnd
    -0.36
    LayoutManager
    -0.36
     fotográfico
    -0.35
     pulumi
    -0.35
    ThroughAttribute
    -0.35
    POSITIVE LOGITS
     mergeFrom
    0.58
     object
    0.57
     للمعارف
    0.55
     entity
    0.53
     person
    0.50
     personage
    0.50
    對象
    0.49
    該当
    0.49
     creature
    0.49
     объект
    0.49
    Activations Density 0.469%

    No Known Activations