Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13720
    Prev
    Next
    INDEX
    Explanations

    references to cases in a clinical or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.72
    клопе
    -0.71
    AnchorStyles
    -0.69
    NewLabel
    -0.68
    mapStateToProps
    -0.67
     bienfaits
    -0.64
     Monfieur
    -0.63
    PerformLayout
    -0.63
     domani
    -0.62
     valmist
    -0.61
    POSITIVE LOGITS
     cases
    4.71
     Cases
    4.23
    Cases
    4.01
    cases
    3.96
     case
    3.69
     CASES
    3.55
     Case
    3.36
    Case
    3.34
     casos
    3.27
    case
    3.25
    Activations Density 0.121%

    No Known Activations