© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10008
    Prev
    Next
    INDEX
    Explanations

    derogatory terms and expressions of frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIAF
    -1.09
     VIAF
    -0.97
    tır
    -0.77
    :]:
    -0.75
    stateProvider
    -0.73
    awtextra
    -0.73
    LinkId
    -0.70
    @[+][
    -0.70
    ::~
    -0.69
     Egli
    -0.69
    POSITIVE LOGITS
     shit
    2.27
     bullshit
    2.04
     fuck
    1.93
     SHIT
    1.90
     fucking
    1.89
     fucked
    1.89
    fuck
    1.86
     crap
    1.85
    Shit
    1.82
     shitty
    1.82
    Activations Density 0.191%

    No Known Activations