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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9575
    Prev
    Next
    INDEX
    Explanations

    themes related to moral and ethical considerations in historical 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
    OfMonth
    -0.61
     cuttings
    -0.56
     Containers
    -0.56
    zech
    -0.54
     nutmeg
    -0.53
     secular
    -0.53
    upuncture
    -0.53
    COUVER
    -0.53
     Tercera
    -0.52
     administrativos
    -0.52
    POSITIVE LOGITS
     Confederate
    1.01
     Southern
    0.98
     southern
    0.91
    Southern
    0.87
     SOUTHERN
    0.82
     Confederacy
    0.82
     South
    0.82
     Civil
    0.82
     Mississippi
    0.80
     Alabama
    0.80
    Activations Density 0.404%

    No Known Activations