© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5699
    Prev
    Next
    INDEX
    Explanations

    words related to folklore and traditional stories

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

    starting with "cr", "br", "fr", "gr", "tr", or "pr"

    np_acts-logits-general · gemini-2.0-flash

    br, cr, fr, gr, tr sounds

    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
    Portail
    -0.63
     getItemId
    -0.59
     intptr
    -0.57
    ური
    -0.56
     posY
    -0.55
    posy
    -0.54
     yPos
    -0.53
    DotNetBar
    -0.52
     Yaman
    -0.51
    fortawesome
    -0.50
    POSITIVE LOGITS
     grève
    0.60
     Tr
    0.55
     Tru
    0.54
     Brüder
    0.53
     Trä
    0.52
     createSprite
    0.52
     Krü
    0.52
     étr
    0.51
    niosek
    0.50
     sprüche
    0.50
    Activations Density 1.624%

    No Known Activations