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. 7-GEMMASCOPE-RES-16K
    6. 8925
    Prev
    Next
    INDEX
    Explanations

    instances of the word "This" indicating important points or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demain
    -0.67
     wikipagina
    -0.59
     enfans
    -0.59
    mauer
    -0.59
     ujednoznacz
    -0.58
     with
    -0.58
     présidenti
    -0.57
     bezpiecze
    -0.55
    ClientRect
    -0.52
     minum
    -0.52
    POSITIVE LOGITS
    ритори
    0.89
    󠁿
    0.80
    This
    0.74
     This
    0.74
    ParallelGroup
    0.74
    itemize
    0.73
     merupakan
    0.73
    ]**
    0.71
    ее
    0.69
    mitter
    0.67
    Activations Density 0.173%

    No Known Activations