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. 15-GEMMASCOPE-RES-16K
    6. 2366
    Prev
    Next
    INDEX
    Explanations

    references to event planning and attendance instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.77
    horabuena
    -0.60
    ysław
    -0.57
    
    -0.56
    ########.
    -0.54
     zalando
    -0.54
    conio
    -0.53
    RunWith
    -0.52
    _))
    -0.51
     '*':
    -0.51
    POSITIVE LOGITS
    RSVP
    0.63
     RSVP
    0.61
     asistentes
    0.59
    PARTICIP
    0.59
     registration
    0.59
     participants
    0.58
     Registration
    0.57
    participants
    0.56
    Participants
    0.56
     participation
    0.56
    Activations Density 0.085%

    No Known Activations