© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 11353
    Prev
    Next
    INDEX
    Explanations

    specific references to investigations, arrests, or legal processes

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

    Tokens after punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    cities and locations

    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
     المعيارى
    -0.75
     AssemblyCulture
    -0.74
     Administrativna
    -0.72
     autorytatywna
    -0.71
     GenerationType
    -0.67
    UrlResolution
    -0.63
    Personensuche
    -0.63
    twimg
    -0.62
     للمعارف
    -0.61
    antası
    -0.61
    POSITIVE LOGITS
    WASHINGTON
    0.63
    Washington
    0.54
     WASHINGTON
    0.52
     Washington
    0.48
    lamabad
    0.47
    LONDON
    0.45
    NEW
    0.41
     by
    0.38
    New
    0.37
    PORT
    0.34
    Activations Density 0.195%

    No Known Activations