© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8452
    Prev
    Next
    INDEX
    Explanations

    modal verbs and expressions of uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.74
     ModelRenderer
    -0.72
    damento
    -0.72
    IntoConstraints
    -0.69
     alfo
    -0.67
     CreateTagHelper
    -0.67
    webElementXpaths
    -0.65
     AppColors
    -0.64
     препратки
    -0.64
    +#+#
    -0.61
    POSITIVE LOGITS
    abat
    0.47
     pretty
    0.47
    rive
    0.44
     dis
    0.44
     it
    0.44
    hre
    0.43
    Basically
    0.43
     basically
    0.43
    vester
    0.43
    ONS
    0.43
    Activations Density 0.435%

    No Known Activations