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. 20-GEMMASCOPE-RES-16K
    6. 5258
    Prev
    Next
    INDEX
    Explanations

    references to specific names or entities, particularly those related to individuals and their works

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

    Tokens preceding a person's last name

    np_acts-logits-general · gemini-2.0-flash

    name followed by surname or identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.60
     visst
    -0.58
    GIVEREF
    -0.57
    ية
    -0.55
     helst
    -0.54
    туаль
    -0.53
     elif
    -0.53
    sno
    -0.50
    addContainerGap
    -0.49
    يتها
    -0.49
    POSITIVE LOGITS
    jspx
    0.73
    elten
    0.73
    GEBURTSDATUM
    0.73
    ]();
    0.73
    WriteTagHelper
    0.71
    ்கள்
    0.66
    WTS
    0.65
    ForKey
    0.65
     dentaire
    0.64
    Sucesor
    0.62
    Activations Density 0.532%

    No Known Activations