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. 4-GEMMASCOPE-RES-16K
    6. 3216
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly parentheses and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onAnimation
    -0.64
     medesimo
    -0.62
     Solon
    -0.56
     sarcoma
    -0.54
     infarction
    -0.53
     aislada
    -0.51
    midler
    -0.51
     Athenians
    -0.50
     gezet
    -0.49
     cittadino
    -0.49
    POSITIVE LOGITS
     مرئيه
    0.84
    Hozzáférés
    0.81
    DeleteBehavior
    0.74
    TableAdapter
    0.74
     становника
    0.73
    Carriera
    0.72
    ]]
    
    0.71
    %]
    0.70
     مشين
    0.70
    ]';
    0.69
    Activations Density 0.336%

    No Known Activations