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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9236
    Prev
    Next
    INDEX
    Explanations

    instances of assistance or support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intervenir
    -0.50
    sibirsk
    -0.45
     award
    -0.45
     one
    -0.44
     appeler
    -0.44
     intervention
    -0.44
     giving
    -0.43
    给了
    -0.42
     only
    -0.42
     vanille
    -0.42
    POSITIVE LOGITS
     EconPapers
    0.92
     ModelExpression
    0.92
    IsContent
    0.89
     protoimpl
    0.85
    RegressionTest
    0.85
    Carriera
    0.84
    
    0.81
    
    0.81
     Akismet
    0.80
    ]--;
    0.79
    Activations Density 0.149%

    No Known Activations