© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 10600
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational policies and strategies

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

    Curriculum and educational subjects

    np_acts-logits-general · gemini-2.0-flash

    school curriculum and subjects

    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
     AssemblyCulture
    -0.61
    mphony
    -0.57
    XtraEditors
    -0.55
     Reverso
    -0.55
    __':
    
    -0.53
    monial
    -0.51
    DockStyle
    -0.50
    SneakyThrows
    -0.48
    ISupport
    -0.46
     jScrollPane
    -0.45
    POSITIVE LOGITS
     curriculum
    1.65
     curricula
    1.39
    curriculum
    1.36
     Curriculum
    1.28
     syllabus
    1.27
    Curriculum
    1.19
     curricular
    1.15
     kurikulum
    1.11
     cur
    1.08
     content
    1.07
    Activations Density 0.118%

    No Known Activations