© 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. 2-GEMMASCOPE-RES-16K
    11. 12929
    Prev
    Next
    INDEX
    Explanations

    the word "bright" in various contexts, as well as specific Russian characters or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.72
     Platform
    -0.62
     platform
    -0.60
    Platform
    -0.59
     PLATFORM
    -0.56
     plateforme
    -0.49
    platform
    -0.48
    AnchorTagHelper
    -0.47
     plataforma
    -0.46
     lã
    -0.46
    POSITIVE LOGITS
    С
    1.13
     С
    1.05
    с
    1.03
     с
    0.86
    сс
    0.47
    ск
    0.44
     therewith
    0.41
    ср
    0.39
    ス
    0.39
    addPreferredGap
    0.39
    Activations Density 0.063%

    No Known Activations