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. 16-GEMMASCOPE-RES-16K
    6. 226
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quantity or frequency, particularly those related to small numbers and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "few" followed by a unit of time or quantity

    np_acts-logits-general · gemini-2.0-flash

    small quantities or periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Slf
    -0.58
    C
    -0.58
    st
    -0.56
    <em>
    -0.55
     tasche
    -0.55
    לית
    -0.55
     Datenschutzer
    -0.53
     εἰ
    -0.51
    I
    -0.50
    i
    -0.49
    POSITIVE LOGITS
     dozen
    1.48
    dozen
    1.29
     hundred
    1.13
     wenige
    1.04
     few
    0.98
     FEW
    0.97
     CreateTagHelper
    0.96
     Мексичка
    0.95
    few
    0.94
     thousand
    0.92
    Activations Density 0.084%

    No Known Activations