© 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. 3524
    Prev
    Next
    INDEX
    Explanations

    repeated phrases indicating possession or affiliation

    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
     zijne
    -0.55
     ModelExpression
    -0.55
     mijne
    -0.54
    writeField
    -0.54
    DOCTYPE
    -0.52
     Signalez
    -0.52
    tagHelperRunner
    -0.51
     nakalista
    -0.49
    WriteAttribute
    -0.48
    SharedCtor
    -0.48
    POSITIVE LOGITS
     part
    1.45
     parte
    1.13
    part
    1.11
     часть
    1.09
     Teil
    1.03
     частью
    0.99
    Parte
    0.96
    Part
    0.94
     parts
    0.94
     PART
    0.93
    Activations Density 0.169%

    No Known Activations