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. 15-GEMMASCOPE-RES-16K
    6. 12788
    Prev
    Next
    INDEX
    Explanations

    instances or formats related to structured data and programming syntax

    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
    <eos>
    -0.91
     “
    -0.63
     Van
    -0.60
    破
    -0.53
     Приступљено
    -0.52
     Shar
    -0.51
    婆
    -0.51
    ↵↵↵
    -0.50
    ↵↵
    -0.50
    җ
    -0.49
    POSITIVE LOGITS
    tvguidetime
    0.97
     المعيارى
    0.86
     незавершена
    0.85
     HasFactory
    0.84
    MessageTagHelper
    0.79
    trui
    0.75
     MainAxisSize
    0.75
    findpost
    0.75
     venons
    0.74
     myſelf
    0.74
    Activations Density 1.514%

    No Known Activations