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. 0-GEMMASCOPE-RES-16K
    6. 7539
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Meanwhile"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.86
    ohner
    -0.77
     समीक्षाओं
    -0.71
    UnsafeEnabled
    -0.70
    StartTag
    -0.68
    RDONLY
    -0.68
    omitempty
    -0.67
     PicClick
    -0.67
    SBATCH
    -0.66
    dedores
    -0.66
    POSITIVE LOGITS
     Mean
    0.63
     meanwhile
    0.56
    Mean
    0.55
     تضيفلها
    0.53
     Meanwhile
    0.53
    bd
    0.52
    zellan
    0.52
     Paglinawan
    0.52
    val
    0.51
     MonoBehaviour
    0.49
    Activations Density 0.185%

    No Known Activations