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. 7442
    Prev
    Next
    INDEX
    Explanations

    references to user interface elements or components related to UI frameworks

    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
    CPtr
    -0.71
     fufficient
    -0.66
     poffible
    -0.66
     hunne
    -0.64
     fhort
    -0.61
     Majefty
    -0.60
    ("/{
    -0.60
     Vall
    -0.60
     fometimes
    -0.58
     pleaſure
    -0.58
    POSITIVE LOGITS
    ui
    2.52
     ui
    1.43
    hui
    0.80
     Ui
    0.74
     shui
    0.73
    AndEndTag
    0.73
     Tui
    0.72
     nui
    0.71
    uis
    0.69
    lui
    0.69
    Activations Density 0.046%

    No Known Activations