© 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. 2-GEMMASCOPE-RES-16K
    11. 8696
    Prev
    Next
    INDEX
    Explanations

    references to various sectors and their characteristics or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.49
    Spoljašnje
    -0.45
    Simult
    -0.41
     LCCN
    -0.40
     notizie
    -0.39
    TOTAL
    -0.39
    RequestQueue
    -0.39
     totale
    -0.39
    RestTemplate
    -0.39
     Tj
    -0.38
    POSITIVE LOGITS
     sector
    0.94
     SECTOR
    0.76
     Sector
    0.76
     sectoral
    0.70
    Sector
    0.67
     sectors
    0.67
     sektor
    0.66
    sector
    0.66
     proper
    0.66
    AddHtmlAttribute
    0.66
    Activations Density 0.159%

    No Known Activations