© 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. 10401
    Prev
    Next
    INDEX
    Explanations

    common phrases or structures indicating generalizations about groups of people or conditions

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

    Prepositions such as "of" or "in"

    np_acts-logits-general · gemini-2.0-flash

    of the specifying context

    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
     Stone
    -0.36
     hypothetical
    -0.35
    stone
    -0.34
    ør
    -0.34
    ferrari
    -0.34
    enden
    -0.33
     imperfect
    -0.33
     Multicultural
    -0.32
    PPS
    -0.32
     Ferrari
    -0.32
    POSITIVE LOGITS
     المعيارى
    0.73
    featureID
    0.65
     vectorielle
    0.60
    fjspx
    0.60
    antMatchers
    0.59
    WebServlet
    0.59
     tiden
    0.55
    esgue
    0.55
     mijne
    0.55
     befolk
    0.54
    Activations Density 0.274%

    No Known Activations