© 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. 3-GEMMASCOPE-RES-16K
    11. 11050
    Prev
    Next
    INDEX
    Explanations

    terms related to publishing and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.43
    TestBed
    -0.42
     indicaciones
    -0.41
     sério
    -0.41
    ợn
    -0.40
     condições
    -0.40
     kohta
    -0.39
     şart
    -0.39
    туа
    -0.39
    Ơ
    -0.39
    POSITIVE LOGITS
     publishing
    3.31
     publish
    3.13
     Publishing
    3.05
     Publish
    2.98
    publish
    2.92
    Publishing
    2.89
    Publish
    2.81
    publishing
    2.73
     publishes
    2.61
     publisher
    2.58
    Activations Density 0.106%

    No Known Activations