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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 8570
    Prev
    Next
    INDEX
    Explanations

    quantitative data regarding player performance and scoring statistics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elettrico
    -0.60
     ويكيپيديا
    -0.56
     ddelweddau
    -0.55
    contentLoaded
    -0.54
    AndEndTag
    -0.54
    per
    -0.54
    ########.
    -0.52
    fjspx
    -0.52
     själ
    -0.51
     composizione
    -0.50
    POSITIVE LOGITS
    createTextNode
    0.64
     collectively
    0.60
     comples
    0.55
     total
    0.54
    ⋙
    0.54
     useContext
    0.54
    Trama
    0.54
     cumul
    0.53
    BindView
    0.52
     totaling
    0.52
    Activations Density 0.190%

    No Known Activations