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. 9588
    Prev
    Next
    INDEX
    Explanations

    terms related to special education, disabilities, and interventions for children with specific needs

    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
     HasFactory
    -0.67
     tubeless
    -0.58
     morire
    -0.56
     rivel
    -0.53
    Viitteet
    -0.51
    logous
    -0.51
     ngan
    -0.49
     nemico
    -0.49
     scattata
    -0.48
    DockStyle
    -0.47
    POSITIVE LOGITS
     autism
    1.05
     Autism
    1.03
    Autism
    1.00
     autistic
    0.92
    perger
    0.78
     ASD
    0.76
     spectrum
    0.74
     ау
    0.73
     social
    0.71
     developmental
    0.69
    Activations Density 0.254%

    No Known Activations