© 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. 1441
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or governmental figures and their actions

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

    the word "former"

    np_acts-logits-general · gemini-2.0-flash

    former positions or roles

    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
    beschreibung
    -0.37
    "}")
    -0.36
    gouv
    -0.34
    Vidite
    -0.33
    THERS
    -0.31
    struktion
    -0.31
    laufen
    -0.31
     dör
    -0.30
    aticano
    -0.29
    ρακ
    -0.29
    POSITIVE LOGITS
     former
    2.80
     Former
    2.44
    Former
    2.44
    former
    2.39
     ehemalige
    2.06
     ehemaligen
    2.05
     býval
    1.99
     formerly
    1.91
     ehemal
    1.87
     mantan
    1.82
    Activations Density 0.512%

    No Known Activations