Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 62208
    Prev
    Next
    INDEX
    Explanations

    terms related to misconceptions or incorrect beliefs in a technical context

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

    Boolean values and comparison results in mathematics problems, particularly "False" answers to equality questions or numerical answers to comparison questions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     queſta
    -0.77
     BoxFit
    -0.76
    aarrggbb
    -0.69
    WebVitals
    -0.65
     ddelwed
    -0.65
    
    -0.64
    RegistryLite
    -0.63
     Weiſe
    -0.63
    ロウィン
    -0.63
     fashiola
    -0.63
    POSITIVE LOGITS
     example
    0.40
    twór
    0.29
     No
    0.28
    2
    0.28
    1
    0.28
     examples
    0.28
    Aiheesta
    0.27
    Trả
    0.26
    8
    0.26
     Example
    0.25
    Activations Density 0.015%

    No Known Activations