© 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. 39-GEMMASCOPE-RES-16K
    11. 3078
    Prev
    Next
    INDEX
    Explanations

    quoted speech and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stating
    -0.89
    stated
    -0.80
     stated
    -0.73
    tagHelperRunner
    -0.69
    PerformLayout
    -0.68
    States
    -0.65
    states
    -0.63
    Statements
    -0.63
    Said
    -0.63
     Statements
    -0.63
    POSITIVE LOGITS
     say
    0.95
     says
    0.84
     saya
    0.66
    saya
    0.44
     sys
    0.40
    เดียว
    0.36
    という
    0.35
    っていう
    0.34
    Saya
    0.32
    łoży
    0.32
    Activations Density 0.205%

    No Known Activations