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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10034
    Prev
    Next
    INDEX
    Explanations

    phrases related to people's beliefs and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ätigkeit
    -0.55
     متعلقه
    -0.51
    !*\
    -0.50
    __":
    
    -0.49
    させ
    -0.48
    させる
    -0.47
    らせ
    -0.47
     spécialisée
    -0.46
    roj
    -0.46
     affitto
    -0.46
    POSITIVE LOGITS
    gameserver
    0.81
    tizens
    0.62
    Становништво
    0.61
    Kjelder
    0.61
    yscy
    0.60
    matchCondition
    0.58
     estekak
    0.58
    новништво
    0.56
     lenker
    0.56
     विश्वसनीयता
    0.56
    Activations Density 0.481%

    No Known Activations