Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10883
    Prev
    Next
    INDEX
    Explanations

    keywords related to poverty reduction and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.84
     فريبيس
    -0.73
     Roskov
    -0.68
    setVerticalGroup
    -0.65
    casian
    -0.60
     للاسماء
    -0.59
    Personendaten
    -0.59
    rungsseite
    -0.56
    parsedMessage
    -0.56
    Personensuche
    -0.54
    POSITIVE LOGITS
     uncertainty
    0.92
     violence
    0.90
     poverty
    0.89
     insecurity
    0.84
     instability
    0.82
     disorder
    0.81
     inequality
    0.81
     dysfunction
    0.80
     chaos
    0.78
     corruption
    0.77
    Activations Density 1.051%

    No Known Activations