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. 6485
    Prev
    Next
    INDEX
    Explanations

    references to specific names and terms associated with a brand or product, particularly focused on "snaps" and "sna" constructs

    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
     Muck
    -0.79
     estimés
    -0.79
     Wilma
    -0.77
     REA
    -0.77
     Мексичка
    -0.77
     posX
    -0.75
     Aria
    -0.73
     pü
    -0.72
    toDo
    -0.71
    erl
    -0.71
    POSITIVE LOGITS
     Sna
    0.91
    sna
    0.87
    Sna
    0.80
    chafter
    0.78
     sna
    0.75
    openzeppelin
    0.74
    Datuak
    0.74
    INUM
    0.74
    SQLException
    0.73
     Johnson
    0.71
    Activations Density 0.458%

    No Known Activations