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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8397
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hold" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.76
     Bakker
    -0.74
    PyExc
    -0.69
    ucs
    -0.69
    nyez
    -0.68
     Rasmussen
    -0.65
     bác
    -0.65
    Authors
    -0.63
    getDocument
    -0.62
     Acker
    -0.62
    POSITIVE LOGITS
     hold
    2.13
     Hold
    2.08
     Holds
    2.05
     holds
    2.04
    Hold
    1.99
    holds
    1.98
     HOLD
    1.96
    hold
    1.95
     holding
    1.92
    HOLD
    1.88
    Activations Density 0.068%

    No Known Activations