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. 15-GEMMASCOPE-RES-16K
    6. 12693
    Prev
    Next
    INDEX
    Explanations

    programming control structures and logical conditions within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iconFacebook
    -0.57
    laye
    -0.56
     fufficient
    -0.53
    virons
    -0.51
    DOCTYPE
    -0.51
     Monfieur
    -0.51
    artment
    -0.50
    PhysRevD
    -0.50
    bulo
    -0.50
     wikipagina
    -0.50
    POSITIVE LOGITS
     if
    1.56
    if
    1.41
     nếu
    1.22
     dacă
    1.16
     если
    1.13
    If
    1.09
     If
    1.06
     jika
    1.04
     якщо
    1.03
     hvis
    0.99
    Activations Density 0.050%

    No Known Activations