© 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. 16-GEMMASCOPE-RES-16K
    11. 1079
    Prev
    Next
    INDEX
    Explanations

    arguments and claims presented in a legal context

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

    Followed by a weak verb

    np_acts-logits-general · gemini-2.0-flash

    presenting an argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.83
     Meksiku
    -0.79
     estekak
    -0.70
    WebVitals
    -0.67
    
    -0.62
    IsContent
    -0.61
    GEBURTSDATUM
    -0.61
     numberWith
    -0.58
     '\\;'
    -0.58
    tvguidetime
    -0.57
    POSITIVE LOGITS
     arguments
    1.57
     argument
    1.49
     argumentos
    1.30
     Arguments
    1.29
     argumento
    1.28
    arguments
    1.25
     Argument
    1.24
     argumenta
    1.22
    Argument
    1.20
    argument
    1.17
    Activations Density 0.977%

    No Known Activations