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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 128
    Prev
    Next
    INDEX
    Explanations

    educational resources and materials specifically for teachers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     cimetière
    -0.54
    ScopeManager
    -0.49
    PerformLayout
    -0.49
     BoxDecoration
    -0.49
    fotografía
    -0.47
    DockStyle
    -0.46
     bambú
    -0.46
     cordón
    -0.45
     gql
    -0.44
    úsqueda
    -0.44
    POSITIVE LOGITS
     teaching
    0.83
     pedagogical
    0.81
     classroom
    0.73
     pedagogy
    0.71
     curriculum
    0.70
    teaching
    0.69
    Teaching
    0.68
     Teaching
    0.67
     pedagog
    0.65
     didac
    0.65
    Activations Density 0.332%

    No Known Activations