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. 2-GEMMASCOPE-RES-16K
    6. 15727
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "meeting" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.69
    guenos
    -0.69
    ginal
    -0.67
     hubiese
    -0.65
    polate
    -0.62
    ノロ
    -0.61
    — 
    -0.60
     waard
    -0.58
    Архівовано
    -0.58
    いる
    -0.58
    POSITIVE LOGITS
     meeting
    3.80
     Meeting
    3.59
    Meeting
    3.52
    meeting
    3.44
     MEETING
    3.23
     meetings
    3.13
     Meetings
    2.99
    Meetings
    2.75
    meetings
    2.65
     MEET
    2.55
    Activations Density 0.076%

    No Known Activations