© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8353
    Prev
    Next
    INDEX
    Explanations

    instances of encouragement and expressions of self-doubt in personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    comuna
    -0.32
     Савезне
    -0.32
     joaat
    -0.32
    CppCodeGen
    -0.31
     tartalomajánló
    -0.30
    PropertyChanging
    -0.30
    XtraReports
    -0.30
    忙
    -0.29
    しみ
    -0.29
     productivity
    -0.28
    POSITIVE LOGITS
     daring
    2.14
     berani
    2.11
     bold
    2.03
     brave
    2.00
     courageous
    1.98
     courage
    1.95
     dared
    1.89
     boldness
    1.89
     boldly
    1.84
     bravery
    1.80
    Activations Density 0.532%

    No Known Activations