© 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. 34-GEMMASCOPE-RES-16K
    6. 11142
    Prev
    Next
    INDEX
    Explanations

    sentences containing instructions or guidance on how to perform tasks

    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
    DataPropertyName
    -0.48
     EventArgs
    -0.44
    Хьажоргаш
    -0.41
    もしろ
    -0.40
     дописавши
    -0.40
     Quotes
    -0.37
     <>",
    -0.36
     Roskov
    -0.36
    Quote
    -0.36
    RegressionTest
    -0.36
    POSITIVE LOGITS
     instructions
    2.41
    instructions
    2.13
     Instructions
    2.05
    Instructions
    1.98
     instruction
    1.95
     INSTRUCTIONS
    1.83
     instrucciones
    1.79
    instruction
    1.73
     Instruction
    1.73
     tutorial
    1.64
    Activations Density 0.509%

    No Known Activations