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. 6087
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or distinction among items

    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
    UnsafeEnabled
    -0.69
     lenker
    -0.66
    Personendaten
    -0.66
     Waray
    -0.65
     Phaser
    -0.64
     onAnimation
    -0.63
    arrive
    -0.63
    intios
    -0.62
     ✭✭
    -0.62
    Datuak
    -0.62
    POSITIVE LOGITS
     than
    0.66
     außer
    0.66
     beyond
    0.56
     THAN
    0.55
    )$}
    0.54
     Than
    0.53
    Than
    0.52
     BEYOND
    0.51
     Except
    0.50
     poza
    0.50
    Activations Density 0.295%

    No Known Activations