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. 21-GEMMASCOPE-RES-16K
    6. 253
    Prev
    Next
    INDEX
    Explanations

    references to items and experiences related to parenting and childcare products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    érience
    -0.60
     froide
    -0.59
     protoimpl
    -0.58
     privilégi
    -0.58
    jednoc
    -0.56
    יצד
    -0.55
     nostru
    -0.54
    WaitGroup
    -0.53
     Itself
    -0.52
     bienven
    -0.52
    POSITIVE LOGITS
     them
    0.81
     both
    0.72
     replacements
    0.66
     EVERYTHING
    0.64
     BOTH
    0.64
     everything
    0.61
     TWO
    0.59
     him
    0.57
     extras
    0.57
    mybatisplus
    0.57
    Activations Density 0.235%

    No Known Activations