© 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. 6270
    Prev
    Next
    INDEX
    Explanations

    phrases indicating joint ventures, collaborations, or partnerships

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

    meaning "together" or "shared"

    np_acts-logits-general · gemini-2.0-flash

    joint venture, replacement, statement, tort, effort

    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
     disambiguazione
    -0.43
     wiedzieć
    -0.41
     Szene
    -0.40
     atras
    -0.40
    expliquer
    -0.38
     kumpulan
    -0.38
     masing
    -0.38
    Læs
    -0.35
     ilość
    -0.35
    ęty
    -0.35
    POSITIVE LOGITS
     Joint
    0.94
     joint
    0.92
    joint
    0.85
     JOINT
    0.84
    Joint
    0.82
    JOINT
    0.80
     jointly
    0.74
     مشتر
    0.62
     JV
    0.60
     ब्रेकडाउन
    0.59
    Activations Density 0.174%

    No Known Activations