© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1511
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate action or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faptul
    -0.42
     mainly
    -0.38
     mostly
    -0.33
    fancybox
    -0.33
     thought
    -0.32
     gând
    -0.31
     fakty
    -0.31
     compañ
    -0.30
     few
    -0.30
     verksamhet
    -0.30
    POSITIVE LOGITS
    howto
    0.82
     Administrativna
    0.75
    AsUp
    0.73
    OGND
    0.72
    RenderAtEndOf
    0.71
    VIAF
    0.71
     CreateTagHelper
    0.69
    hyrchwyd
    0.68
     autorytatywna
    0.68
    Proper
    0.67
    Activations Density 0.165%

    No Known Activations