© 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. 37-GEMMASCOPE-RES-16K
    11. 820
    Prev
    Next
    INDEX
    Explanations

    concepts related to market opportunities and competitive advantage in sustainability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.62
    SBATCH
    -0.50
    cticut
    -0.48
    setVerticalGroup
    -0.47
    EndContext
    -0.47
    recated
    -0.44
     nämlich
    -0.42
    oredCriteria
    -0.42
    procedures
    -0.41
     Procedures
    -0.40
    POSITIVE LOGITS
     differentiated
    1.03
     differentiation
    1.02
     value
    1.02
     differentiating
    0.90
     differentiate
    0.85
     diferenci
    0.84
     VALUE
    0.83
    value
    0.81
     Differentiation
    0.80
     differenti
    0.79
    Activations Density 0.278%

    No Known Activations