© 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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2588
    Prev
    Next
    INDEX
    Explanations

    specific Greek words or names associated with neighborhoods and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.57
    Ἄ
    -0.54
    άζ
    -0.53
    ಾಗ
    -0.53
    νή
    -0.52
     himo
    -0.52
    ಾಯ
    -0.51
    ೊ
    -0.51
    νώ
    -0.50
    ṓ
    -0.50
    POSITIVE LOGITS
    NamedQueries
    0.72
    :✨
    0.67
    ⓧ
    0.62
    anskje
    0.59
     kasarigan
    0.59
    Kanpo
    0.57
    hdessä
    0.57
    σεων
    0.56
    μως
    0.55
    ῃ
    0.55
    Activations Density 0.158%

    No Known Activations