© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7487
    Prev
    Next
    INDEX
    Explanations

    components related to pagination and database query setups

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

    'page' and 'pagination'

    np_acts-logits-general · gemini-2.0-flash

    pagination and data listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.57
    CppMethod
    -0.54
    AndEndTag
    -0.48
    exitRule
    -0.48
     прока
    -0.47
     currentValue
    -0.45
    +#+#
    -0.45
     coat
    -0.44
    Priorities
    -0.43
    ModelSerializer
    -0.43
    POSITIVE LOGITS
     pagination
    0.76
     pag
    0.66
    paginate
    0.63
    pagination
    0.63
     paging
    0.62
     Pag
    0.58
     Pagination
    0.56
     分页
    0.56
     page
    0.55
    paginator
    0.55
    Activations Density 0.143%

    No Known Activations