© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4911
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional pain and the struggle with creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtand
    -1.01
     AssemblyCulture
    -1.00
     neceff
    -1.00
     pleaſure
    -0.99
     anſ
    -0.97
     fubject
    -0.96
     Jefus
    -0.96
     himſelf
    -0.94
     chofe
    -0.94
     ſtate
    -0.93
    POSITIVE LOGITS
    tagext
    0.41
     fragile
    0.39
    poe
    0.36
     Is
    0.36
     geográfica
    0.35
     paramInt
    0.35
    LookAnd
    0.34
    col
    0.34
     I
    0.33
    LDR
    0.33
    Activations Density 0.213%

    No Known Activations