© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 7584
    Prev
    Next
    INDEX
    Explanations

    language indicating emotional distress or negative comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéroïdes
    -0.39
    ajoz
    -0.36
    errno
    -0.36
     işe
    -0.32
     Tabasco
    -0.32
     yoğun
    -0.32
     Audiodateien
    -0.32
     įsi
    -0.31
     positifs
    -0.30
     élections
    -0.30
    POSITIVE LOGITS
    @[+][
    0.62
    ніципалі
    0.56
    mybatisplus
    0.55
    dafx
    0.53
     Numerade
    0.53
     Infórmanos
    0.52
    exitRule
    0.52
     AssemblyCompany
    0.52
    المكان
    0.52
     betweenstory
    0.52
    Activations Density 1.122%

    No Known Activations