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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 4918
    Prev
    Next
    INDEX
    Explanations

    references to community significance and local culture

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

    Followed by statistics or quantities

    np_acts-logits-general · gemini-2.0-flash

    population and demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ISNI
    -0.61
    Madagascar
    -0.55
    libft
    -0.53
    ัติ
    -0.51
    VertexArray
    -0.50
    WithIOException
    -0.49
     aclar
    -0.49
    ativement
    -0.49
    Erreferentziak
    -0.48
    internal
    -0.48
    POSITIVE LOGITS
     residents
    1.20
     locals
    1.14
     town
    1.09
     inhabitants
    1.06
     neighborhoods
    1.05
     towns
    1.03
     suburb
    0.99
     suburbs
    0.98
     population
    0.96
    residents
    0.94
    Activations Density 0.426%

    No Known Activations