© 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. 17-GEMMASCOPE-RES-16K
    6. 1482
    Prev
    Next
    INDEX
    Explanations

    testimony or responses related to legal or official proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sobretudo
    -0.68
     Whilst
    -0.65
    Whilst
    -0.64
     Firstly
    -0.63
    vellous
    -0.62
     Organiser
    -0.61
    behaviour
    -0.59
     whilst
    -0.58
     lccn
    -0.58
     urgently
    -0.58
    POSITIVE LOGITS
     gettin
    0.63
     bezeichneter
    0.61
     ***!
    0.59
    Donnie
    0.59
    MessageOf
    0.58
     fellas
    0.58
     lookin
    0.57
     Thra
    0.57
     Donnie
    0.57
    ghum
    0.57
    Activations Density 0.321%

    No Known Activations