© 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. 7-GEMMASCOPE-RES-16K
    6. 15939
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.52
     souci
    -0.40
     suivi
    -0.38
     cumplido
    -0.38
    vertrag
    -0.37
    miljø
    -0.36
     llantas
    -0.36
     AssemblyProduct
    -0.35
     veicolo
    -0.35
     comigo
    -0.35
    POSITIVE LOGITS
    WireFormatLite
    0.60
     gynhyrchwyd
    0.54
     Walkover
    0.52
    PathVariable
    0.49
    DockStyle
    0.49
     الحره
    0.48
    存于互联网档案馆
    0.48
     صوتيه
    0.47
    InputBorder
    0.47
    disposing
    0.46
    Activations Density 0.453%

    No Known Activations