© 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. 25-GEMMASCOPE-RES-16K
    11. 15743
    Prev
    Next
    INDEX
    Explanations

    phrases indicating versions or editions of documents and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complètes
    -0.42
     particulières
    -0.41
     Abonnez
    -0.41
     financiero
    -0.41
     financeiro
    -0.40
     traces
    -0.40
     sorteo
    -0.39
     supérieures
    -0.38
     actuelles
    -0.38
     inscripción
    -0.38
    POSITIVE LOGITS
    ніципалі
    0.61
    NameInMap
    0.54
    󠁣
    0.53
    enumi
    0.51
    yarnpkg
    0.49
    RTGC
    0.48
    MigrationBuilder
    0.46
    MethodManager
    0.45
     kasarigan
    0.44
    ArgumentParser
    0.44
    Activations Density 0.753%

    No Known Activations