© 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. 24-GEMMASCOPE-RES-16K
    11. 2158
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their affiliations

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

    meaning "previous" or "former"

    np_acts-logits-general · gemini-2.0-flash

    former positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}")
    -0.32
    Vidite
    -0.29
     exist
    -0.26
    responseCode
    -0.25
     car
    -0.25
     oprav
    -0.24
     surface
    -0.24
     riding
    -0.24
    gemeinden
    -0.24
     sei
    -0.23
    POSITIVE LOGITS
     former
    1.33
     Former
    1.27
    Former
    1.26
    former
    1.18
     býval
    1.13
     ehemaligen
    1.13
     ehemalige
    1.09
     retired
    1.09
     ehemal
    1.02
     mantan
    1.02
    Activations Density 0.512%

    No Known Activations