© 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. 31-GEMMASCOPE-RES-16K
    11. 8071
    Prev
    Next
    INDEX
    Explanations

    expressions of annoyance or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    profane or vulgar language, particularly curse words and aggressive expletives.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    неопр
    -0.44
    mappedBy
    -0.40
    CompleteListener
    -0.40
    unnitel
    -0.40
    æder
    -0.38
     CascadeType
    -0.37
     newOwner
    -0.36
    HttpStatusCode
    -0.35
    ślę
    -0.33
     поступа
    -0.33
    POSITIVE LOGITS
     damn
    1.39
     hell
    1.32
     goddamn
    1.25
     fucking
    1.22
     damned
    1.18
    damn
    1.15
     fuck
    1.14
     freaking
    1.13
     fuckin
    1.13
     DAMN
    1.10
    Activations Density 0.190%

    No Known Activations