© 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. 27-GEMMASCOPE-RES-16K
    6. 10088
    Prev
    Next
    INDEX
    Explanations

    parameters and characteristics in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     होते
    -0.32
     Fotografía
    -0.30
    ülés
    -0.30
     crí
    -0.30
    parentNode
    -0.29
     partea
    -0.29
    "}")
    -0.28
    ülé
    -0.28
    yttää
    -0.27
     REFR
    -0.27
    POSITIVE LOGITS
     involved
    0.93
     Involved
    0.88
    involved
    0.83
     propOrder
    0.78
    parsedMessage
    0.77
     included
    0.74
     offered
    0.73
     INVOLVED
    0.73
    
    0.71
     Included
    0.69
    Activations Density 0.616%

    No Known Activations