© 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 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. 8085
    Prev
    Next
    INDEX
    Explanations

    phrases related to mortality and existential themes

    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
     nakalista
    -0.63
     harem
    -0.60
    كويكب
    -0.59
    Notae
    -0.59
     galore
    -0.56
     SHIT
    -0.56
    chesse
    -0.54
    Shit
    -0.53
    shit
    -0.52
    AddHtmlAttribute
    -0.52
    POSITIVE LOGITS
    LookAnd
    0.49
    DIPSETTING
    0.33
    elemField
    0.29
    addImage
    0.29
    UserScript
    0.29
    makeText
    0.28
     CURIAM
    0.27
     výkon
    0.27
     SwiftUI
    0.27
     lift
    0.26
    Activations Density 0.226%

    No Known Activations