© 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. 23-GEMMASCOPE-RES-16K
    11. 9207
    Prev
    Next
    INDEX
    Explanations

    discussions centered around personal purpose and decision-making that involve financial implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zier
    -0.37
     hoping
    -0.33
     Sorge
    -0.33
    ély
    -0.32
    ug
    -0.32
    よ
    -0.32
    uck
    -0.32
    ile
    -0.31
     Pil
    -0.31
    ientemente
    -0.31
    POSITIVE LOGITS
     المعيارى
    0.68
    Personendaten
    0.67
     queſta
    0.65
     ويكيميديا
    0.64
    XmlAccessType
    0.63
     ModelExpression
    0.63
    principalTable
    0.61
    IVEREF
    0.60
    parsedMessage
    0.57
     HasFactory
    0.56
    Activations Density 0.515%

    No Known Activations