© 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. 12-GEMMASCOPE-RES-16K
    11. 3032
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs related to integer and long data types and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.47
    PMailer
    -0.38
     zaj
    -0.36
     estekak
    -0.33
     büy
    -0.33
    COMPOSITION
    -0.33
     tár
    -0.33
     continuare
    -0.32
     daarvoor
    -0.31
    Composition
    -0.31
    POSITIVE LOGITS
    interopRequire
    0.81
    NSNumber
    0.75
     CreateTagHelper
    0.66
    RectangleBorder
    0.65
     valueOf
    0.58
     defaultstate
    0.57
    valueOf
    0.57
    fortawesome
    0.53
    Sprintf
    0.52
    PasswordEncoder
    0.52
    Activations Density 0.244%

    No Known Activations