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. 3-GEMMASCOPE-RES-16K
    6. 10062
    Prev
    Next
    INDEX
    Explanations

    the word "personally" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ので
    -0.69
    ■■
    -0.68
     Wylie
    -0.65
    phine
    -0.65
     alimenta
    -0.64
     étend
    -0.63
    enseignement
    -0.63
    NamedQueries
    -0.63
     ise
    -0.62
     Wadsworth
    -0.62
    POSITIVE LOGITS
     שוליים
    0.92
     المعيارى
    0.87
    LayoutPanel
    0.78
     acres
    0.72
    日閲覧
    0.71
     Pct
    0.68
    GOTREF
    0.67
     Sargent
    0.64
    醐
    0.62
    zczegól
    0.62
    Activations Density 0.149%

    No Known Activations