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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 15095
    Prev
    Next
    INDEX
    Explanations

    details related to events, meetings, and their associated costs or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.79
     myſelf
    -0.76
     Majefty
    -0.67
     Jefus
    -0.66
     faſt
    -0.66
    VideoCapture
    -0.65
     eqn
    -0.65
     cref
    -0.65
     ſeveral
    -0.65
     Efq
    -0.64
    POSITIVE LOGITS
     Join
    0.56
     &___
    0.55
    Join
    0.55
    complexContent
    0.51
    webElementXpaths
    0.51
    mergeFrom
    0.48
     BaseController
    0.46
    couvrez
    0.46
    ọi
    0.46
    Quieres
    0.45
    Activations Density 0.483%

    No Known Activations