© 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. 15-GEMMASCOPE-RES-16K
    11. 921
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores and characters that represent attributes or parameters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotivaciones
    -1.07
    majánló
    -0.86
     beſch
    -0.84
     verſch
    -0.81
     increí
    -0.80
     pérd
    -0.79
     rajut
    -0.78
     herido
    -0.77
    InputBorder
    -0.77
     testigo
    -0.76
    POSITIVE LOGITS
    WEBPACK
    0.52
     BrowserModule
    0.45
    NEVER
    0.42
    FB
    0.42
    ®
    0.41
    Never
    0.41
    NOT
    0.41
    MAX
    0.40
    FI
    0.40
    \_
    0.40
    Activations Density 0.295%

    No Known Activations