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. 6443
    Prev
    Next
    INDEX
    Explanations

    references to family and personal background

    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
    年轻人
    -0.46
     élèves
    -0.44
     Students
    -0.43
     leerlingen
    -0.43
     protégé
    -0.42
    弟子
    -0.42
    新人
    -0.42
     students
    -0.40
     jóvenes
    -0.40
     rookies
    -0.39
    POSITIVE LOGITS
     parents
    3.04
     parent
    2.88
     father
    2.78
     mother
    2.71
     dad
    2.63
     mom
    2.59
     Parents
    2.51
     fathers
    2.49
    parents
    2.45
    parent
    2.44
    Activations Density 0.645%

    No Known Activations