© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4969
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "hold" and its various forms, particularly in phrases related to accountability and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    genossen
    -0.78
     bác
    -0.68
    PyExc
    -0.68
    Pis
    -0.68
    ucar
    -0.67
    EEN
    -0.65
    ccn
    -0.65
    Authors
    -0.64
     jSON
    -0.64
    blumen
    -0.63
    POSITIVE LOGITS
     Holds
    1.43
     Hold
    1.43
    holds
    1.42
     holds
    1.42
     Holden
    1.41
     hold
    1.41
     HOLD
    1.35
    Hold
    1.33
    HOLD
    1.32
     Holding
    1.31
    Activations Density 0.088%

    No Known Activations