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. 15120
    Prev
    Next
    INDEX
    Explanations

    references to family interactions and shared meals

    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
     abz
    -0.55
    })();
    
    -0.54
    ății
    -0.54
    assertArray
    -0.51
     peup
    -0.51
     digress
    -0.51
    êng
    -0.50
    längerung
    -0.50
    NavController
    -0.50
     كومونز
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.58
    enjoy
    0.56
     disfrutar
    0.56
     Réponses
    0.54
     enjoying
    0.53
    makeConstraints
    0.52
    MessageOf
    0.51
     Enjoy
    0.50
    Enjoy
    0.50
     enjoy
    0.49
    Activations Density 0.172%

    No Known Activations