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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 2331
    Prev
    Next
    INDEX
    Explanations

    references to specific points in time or conditions related to changes and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngua
    -0.53
    IsPostBack
    -0.50
    hesh
    -0.49
    onets
    -0.48
    ítulo
    -0.47
    ]--;
    -0.47
     Signalez
    -0.45
     IActionResult
    -0.45
    ViewInit
    -0.43
    atorias
    -0.43
    POSITIVE LOGITS
     then
    2.20
     wtedy
    1.98
     тогда
    1.91
     entonces
    1.90
    then
    1.77
     allora
    1.77
     Тогда
    1.68
     Then
    1.63
    Тогда
    1.57
     então
    1.56
    Activations Density 0.411%

    No Known Activations