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. 9205
    Prev
    Next
    INDEX
    Explanations

    terms related to mythology, mathematics, and scientific concepts

    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
    mathit
    -0.81
     Dario
    -0.80
    ton
    -0.77
     }}"></
    -0.75
     Overton
    -0.72
     Yad
    -0.72
    Dario
    -0.71
     Firefly
    -0.70
    <em>
    -0.70
    vill
    -0.70
    POSITIVE LOGITS
    '},
    
    0.88
     Rodrigues
    0.79
    CELONA
    0.79
     NDEBUG
    0.76
    ••
    0.73
    aians
    0.73
     Stern
    0.72
    ••••
    0.71
    -),
    0.71
     ODS
    0.71
    Activations Density 1.601%

    No Known Activations