© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27830
    Prev
    Next
    INDEX
    Explanations

    the presence of specific markers or formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Order, 7, 0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mois
    -0.60
    AVC
    -0.58
    resaid
    -0.57
     Mojo
    -0.57
    DAOImpl
    -0.56
     moe
    -0.56
    خش
    -0.56
     Euse
    -0.55
    Navbar
    -0.55
    tellt
    -0.55
    POSITIVE LOGITS
     around
    0.81
     circled
    0.77
    AddTagHelper
    0.74
    around
    0.74
    circling
    0.71
     autour
    0.70
     circling
    0.68
     circle
    0.66
     round
    0.66
     circumference
    0.65
    Activations Density 0.043%

    No Known Activations