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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14785
    Prev
    Next
    INDEX
    Explanations

    phrases indicating totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.80
     ognuno
    -0.73
     genoux
    -0.65
     ciascuno
    -0.63
     acuer
    -0.62
     exemplu
    -0.58
     chacun
    -0.58
     pregunto
    -0.56
     cérami
    -0.54
    adaptiveStyles
    -0.53
    POSITIVE LOGITS
     major
    1.08
     aspects
    1.07
     relevant
    0.81
     four
    0.80
     three
    0.79
     facets
    0.75
     six
    0.74
     five
    0.73
     pertinent
    0.73
     current
    0.73
    Activations Density 0.219%

    No Known Activations