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. 459
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "following," indicating it focuses on enumerating steps, actions, or items in a sequence

    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
     pouvoirs
    -0.73
     touristes
    -0.72
     larmes
    -0.69
     ddelweddau
    -0.69
     vägen
    -0.68
     partea
    -0.67
    medriver
    -0.66
    afficheront
    -0.66
     picioare
    -0.66
     للمعارف
    -0.66
    POSITIVE LOGITS
     items
    0.77
     three
    0.76
     two
    0.75
    ⬇️
    0.74
     types
    0.70
     four
    0.66
     kinds
    0.64
    👇
    0.63
     additional
    0.63
    Folgende
    0.62
    Activations Density 0.195%

    No Known Activations