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. 2-GEMMASCOPE-RES-16K
    6. 15912
    Prev
    Next
    INDEX
    Explanations

    phrases associated with memorable experiences and cozy settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autobuses
    -0.46
     fiches
    -0.46
     sortes
    -0.45
     damals
    -0.45
    İstinadlar
    -0.45
     loja
    -0.45
    凄く
    -0.44
     pictograms
    -0.44
    Controllo
    -0.43
    orses
    -0.43
    POSITIVE LOGITS
     beginnetje
    0.86
     дописавши
    0.69
     виправивши
    0.68
    __":
    
    0.67
    lielmo
    0.63
    ِّف
    0.63
    __':
    
    0.62
    TypedDataSet
    0.60
     initComponents
    0.59
    WindowConstants
    0.59
    Activations Density 0.482%

    No Known Activations