© 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. 2-GEMMASCOPE-RES-16K
    11. 11571
    Prev
    Next
    INDEX
    Explanations

    the word "ever" and its variations, indicating a focus on expressions of time or occurrence

    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
    bootstrapcdn
    -0.52
    oa̍t
    -0.43
    mobileqq
    -0.43
     bior
    -0.41
     ſtate
    -0.41
    IntoConstraints
    -0.40
     Orchid
    -0.40
     Eſ
    -0.40
    DMC
    -0.40
    IsMutable
    -0.40
    POSITIVE LOGITS
     ever
    4.59
    ever
    3.59
     Ever
    3.53
     EVER
    3.52
    Ever
    3.48
    EVER
    2.94
     jemals
    2.39
     evermore
    2.03
     ooit
    1.97
     jamais
    1.94
    Activations Density 0.078%

    No Known Activations