© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5512
    Prev
    Next
    INDEX
    Explanations

    JavaScript programming functions, particularly those dealing with objects and arrays

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

    JavaScript object properties and methods

    np_acts-logits-general · gemini-2.0-flash

    object properties

    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
    exitRule
    -0.39
     defaultstate
    -0.38
    ObservableList
    -0.37
    SuspendLayout
    -0.36
     nonatomic
    -0.36
    typeorm
    -0.34
    ckså
    -0.34
    Betyg
    -0.34
    endphp
    -0.34
    instancetype
    -0.33
    POSITIVE LOGITS
    stringify
    0.69
    PrototypeOf
    0.65
    keys
    0.56
    Toponymie
    0.55
     keys
    0.55
    VIAF
    0.55
     Keys
    0.54
    Keys
    0.54
    listdir
    0.50
    indd
    0.49
    Activations Density 0.212%

    No Known Activations