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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114120
    Prev
    Next
    INDEX
    Explanations

    HTML comment markers

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

    HTML comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     MainAxisSize
    -0.56
    出版年
    -0.51
     pleaſure
    -0.50
    Général
    -0.45
    +#+#
    -0.45
    bufio
    -0.45
     виправивши
    -0.45
    PhysRevD
    -0.44
    SpringRunner
    -0.43
    tvguidetime
    -0.43
    POSITIVE LOGITS
    <!--
    1.55
     <!--
    1.11
    ><!--
    1.05
    "><!--
    0.86
    /*
    0.81
    <!--
    
    0.81
    {/*
    0.78
    __(/*!
    0.75
    /**
    0.75
    //
    0.71
    Activations Density 0.007%

    No Known Activations