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. 16146
    Prev
    Next
    INDEX
    Explanations

    instances of verbs and actions related to existence and condition

    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
    9
    -0.47
     
    -0.46
    m
    -0.45
     the
    -0.44
    kan
    -0.43
    -
    -0.43
    al
    -0.43
    ano
    -0.43
    3
    -0.43
    &
    -0.42
    POSITIVE LOGITS
     Савезне
    1.17
    hyrchwyd
    1.16
    GEBURTSDATUM
    1.07
    ViewFeatures
    1.02
     disambiguazione
    0.97
    StoreMessageInfo
    0.97
     autorytatywna
    0.96
     betweenstory
    0.94
     يتيمه
    0.94
    rawDesc
    0.94
    Activations Density 0.297%

    No Known Activations