© 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. 31-GEMMASCOPE-RES-16K
    6. 2681
    Prev
    Next
    INDEX
    Explanations

    elements related to logical reasoning and judgment within arguments

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

    words that express caution, restraint, or reasonable judgment.

    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
    IBOutlet
    -0.48
    ServiceModel
    -0.35
     betweenstory
    -0.34
    queryInterface
    -0.34
     gärna
    -0.33
    }],
    
    -0.33
     hâte
    -0.32
    ButterKnife
    -0.32
    ürm
    -0.32
    DockStyle
    -0.31
    POSITIVE LOGITS
     smart
    2.13
     wise
    1.98
     smarter
    1.83
    smart
    1.82
     intelligent
    1.76
     smartest
    1.75
     inteligente
    1.74
     Smart
    1.73
     wiser
    1.72
     shrewd
    1.72
    Activations Density 0.566%

    No Known Activations