© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1727
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or constructs

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

    Code-related characters and symbols

    np_acts-logits-general · gemini-2.0-flash

    data associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.64
    EDEFAULT
    -0.60
    Tikang
    -0.59
     يتيمه
    -0.59
    UnsafeEnabled
    -0.55
    MigrationBuilder
    -0.50
    UnusedPrivate
    -0.49
     Efq
    -0.49
     RoutedEventArgs
    -0.47
     propOrder
    -0.47
    POSITIVE LOGITS
    Eloquent
    0.56
    JoinColumn
    0.55
    ManyToOne
    0.49
    WithMany
    0.47
    ISupport
    0.44
    Hozzáférés
    0.42
     connections
    0.42
     associations
    0.42
    WEBPACK
    0.41
     association
    0.40
    Activations Density 0.146%

    No Known Activations