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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53728
    Prev
    Next
    INDEX
    Explanations

    references to communication and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    requests and inquiries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     visibles
    -0.47
    MessageTagHelper
    -0.45
    subpackage
    -0.44
     partenza
    -0.41
    ataire
    -0.41
     posters
    -0.40
     Résultat
    -0.40
     visible
    -0.40
    ībā
    -0.40
     ContentValues
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.80
     asking
    0.79
     announcing
    0.78
     requesting
    0.76
    asking
    0.75
     informing
    0.73
    Telling
    0.72
    Asking
    0.71
     congrat
    0.71
     мәкал
    0.71
    Activations Density 0.482%

    No Known Activations