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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 13902
    Prev
    Next
    INDEX
    Explanations

    references to training and support in educational or professional contexts

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

    Mentoring, coaching, guidance, or supervision

    np_acts-logits-general · gemini-2.0-flash

    personal guidance and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.80
    GEBURTSDATUM
    -0.65
    ConstraintMaker
    -0.65
     ivelany
    -0.60
    MigrationBuilder
    -0.60
    afficheront
    -0.56
    ollectionView
    -0.55
     ligiloj
    -0.54
     nahilalakip
    -0.54
     iprot
    -0.53
    POSITIVE LOGITS
     mentoring
    1.69
     mentorship
    1.58
     mentor
    1.57
     mentors
    1.45
     Mentoring
    1.36
     guidance
    1.36
    Ment
    1.32
     coaching
    1.26
     Mentor
    1.24
    Mentor
    1.22
    Activations Density 0.226%

    No Known Activations