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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2038
    Prev
    Next
    INDEX
    Explanations

    recurring themes related to online contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.99
     a
    -0.81
     an
    -0.75
     both
    -0.65
     multiple
    -0.64
     all
    -0.61
     various
    -0.57
     their
    -0.56
     full
    -0.56
     front
    -0.55
    POSITIVE LOGITS
    #+#
    0.80
    ungguhnya
    0.65
    poptosis
    0.65
    orexia
    0.65
     noastră
    0.61
    SourceChecksum
    0.61
     anhyd
    0.61
     ONS
    0.61
     aorta
    0.61
    NamedQuery
    0.61
    Activations Density 0.118%

    No Known Activations