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. 17-GEMMASCOPE-RES-16K
    6. 7208
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions of completion or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attempt
    -0.68
     ability
    -0.67
     Allow
    -0.65
     Try
    -0.65
     попыта
    -0.63
    ecé
    -0.63
     Trying
    -0.63
     memungkinkan
    -0.63
     permettre
    -0.59
     tendency
    -0.58
    POSITIVE LOGITS
     estekak
    0.91
    ReusableCell
    0.79
    GEBURTSDATUM
    0.75
     оригіналу
    0.71
     виправивши
    0.69
     WaitForSeconds
    0.69
     kasarigan
    0.68
     CreateTagHelper
    0.67
    存于互联网档案馆
    0.66
     HasFactory
    0.65
    Activations Density 0.221%

    No Known Activations