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. 10-GEMMASCOPE-RES-16K
    6. 2553
    Prev
    Next
    INDEX
    Explanations

    sentences discussing achievements and challenges in various contexts, particularly focusing on concepts of success, value, and scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myself
    -0.69
     yourself
    -0.61
     personally
    -0.60
    myself
    -0.58
     personal
    -0.55
     Kopp
    -0.49
     ourselves
    -0.48
     personalmente
    -0.48
     oneself
    -0.48
     cattle
    -0.47
    POSITIVE LOGITS
     تضيفلها
    1.02
    tvguidetime
    0.93
    ValueStyle
    0.90
     صوتيه
    0.86
    Personensuche
    0.85
     its
    0.74
    AddTagHelper
    0.71
    المناصب
    0.70
    WriteTagHelper
    0.70
     kasarigan
    0.69
    Activations Density 1.097%

    No Known Activations