Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6193
    Prev
    Next
    INDEX
    Explanations

    elements related to configurations and options in user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    LabelTagHelper
    -0.50
     CreateTagHelper
    -0.48
    tagHelperRunner
    -0.46
     useAppContext
    -0.46
    onAttach
    -0.45
    formaz
    -0.44
     Forgot
    -0.44
     influencing
    -0.43
     onBind
    -0.43
    keyColumn
    -0.43
    POSITIVE LOGITS
     Others
    0.83
    Others
    0.81
    OTHERS
    0.76
    それとも
    0.71
     OTHERS
    0.70
    别的
    0.68
    None
    0.68
    others
    0.68
    WebServlet
    0.68
     Other
    0.67
    Activations Density 0.510%

    No Known Activations