Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1020
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "hold" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "hold" or variations of it

    np_acts-logits-general · gemini-2.0-flash

    holding things or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ➟
    -0.49
    Personensuche
    -0.47
    électricité
    -0.46
    contentLoaded
    -0.44
     Ames
    -0.42
     Mahesh
    -0.42
     Diab
    -0.42
     amor
    -0.41
     Smar
    -0.40
     bParam
    -0.40
    POSITIVE LOGITS
     hold
    1.05
     Holding
    1.04
     holds
    1.04
    Hold
    1.03
     Hold
    1.03
    Holding
    1.02
     Holds
    1.02
    hold
    1.01
    holding
    1.01
     holding
    0.97
    Activations Density 0.124%

    No Known Activations