© 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. 31-GEMMASCOPE-RES-16K
    11. 483
    Prev
    Next
    INDEX
    Explanations

    references to "real" concepts or situations, particularly in the context of practicality or authenticity

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

    the phrase "real" followed by a noun or adjective to describe something authentic or practical.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prisma
    -0.45
    Abitanti
    -0.41
    rometry
    -0.41
    期
    -0.41
    
    -0.40
    Genesis
    -0.40
    Principle
    -0.40
    reid
    -0.39
     sinn
    -0.38
    popo
    -0.38
    POSITIVE LOGITS
     real
    0.78
     estate
    0.63
     REAL
    0.63
    ThroughAttribute
    0.63
    Real
    0.62
     Real
    0.62
     reales
    0.61
    real
    0.60
     echten
    0.59
     vraie
    0.59
    Activations Density 0.095%

    No Known Activations