© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 10104
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "one" or singularity, often in the context of emphasizing uniqueness or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stances
    -0.29
    Слайд
    -0.29
    weds
    -0.29
     letech
    -0.28
    eners
    -0.28
     surroundings
    -0.28
    ὗ
    -0.28
     Provide
    -0.27
    que
    -0.27
    Provide
    -0.27
    POSITIVE LOGITS
    styleType
    0.73
     cannot
    0.68
     might
    0.67
    IntoConstraints
    0.64
    tagHelperRunner
    0.62
     mustn
    0.59
     hundred
    0.58
     wonders
    0.58
     needn
    0.58
    NewUrlParser
    0.57
    Activations Density 0.156%

    No Known Activations