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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4607
    Prev
    Next
    INDEX
    Explanations

    phrases related to personalized learning experiences and educational support

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

    courses or learning platforms

    np_acts-logits-general · gemini-2.0-flash

    course learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gruss
    -0.48
    ษัท
    -0.47
    туга
    -0.47
     bezeichneter
    -0.46
     Haft
    -0.46
     CreateTagHelper
    -0.46
    AnchorTagHelper
    -0.45
    windowFixed
    -0.44
    发表于
    -0.44
     Mendelssohn
    -0.43
    POSITIVE LOGITS
     course
    1.15
     Course
    1.15
     learning
    1.13
     Learning
    1.09
     courses
    1.07
    course
    1.05
    Course
    1.05
    Learning
    1.04
    learning
    1.00
     Courses
    0.98
    Activations Density 0.181%

    No Known Activations