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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11416
    Prev
    Next
    INDEX
    Explanations

    important terms related to business and organizational structures

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

    Word or phrase before "is/of/from"

    np_acts-logits-general · gemini-2.0-flash

    roles andconcepts

    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
    цездатний
    -0.68
    transQ
    -0.66
     męska
    -0.60
     myſelf
    -0.59
    脚注の使い方
    -0.59
     Wikiseite
    -0.59
     ffilmiau
    -0.59
    帖最后由
    -0.56
     <<<<<<<<<<<<<<
    -0.56
     wikipagina
    -0.55
    POSITIVE LOGITS
    ɵ
    0.44
     fund
    0.43
     body
    0.42
     hur
    0.42
     ro
    0.41
    -
    0.41
     pension
    0.40
     spo
    0.39
    ândia
    0.39
     fin
    0.39
    Activations Density 0.354%

    No Known Activations