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. 12-GEMMASCOPE-RES-16K
    6. 11965
    Prev
    Next
    INDEX
    Explanations

    complex clauses and relationships within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nonatomic
    -0.60
     Roots
    -0.59
     ***!
    -0.58
    BeginInit
    -0.56
    annte
    -0.53
    ,:);
    -0.51
     />";
    -0.51
    Roots
    -0.50
     uLocal
    -0.50
     nonatomic
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.55
    談社
    0.51
    landais
    0.50
     Zelanda
    0.50
     архивлан
    0.49
    Penjelasan
    0.49
    ソッド
    0.49
    Rptr
    0.48
    Externé
    0.46
     Corbu
    0.45
    Activations Density 0.721%

    No Known Activations