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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3794
    Prev
    Next
    INDEX
    Explanations

    biological terms related to bacteria and infections

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

    Start of URLs or code snippets

    np_acts-logits-general · gemini-2.0-flash

    US patient genes, URLs, barazza, Gastrointestinal

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    Datuak
    -0.63
    </strong>
    -0.53
    </em>
    -0.49
    </b>
    -0.47
    </i>
    -0.47
    AntiForgeryToken
    -0.45
    Véxase
    -0.45
     tirantes
    -0.44
     AssemblyCompany
    -0.43
     OFDb
    -0.43
    POSITIVE LOGITS
    uxxxx
    0.76
    tagHelperRunner
    0.62
    \{\\
    0.54
    contentLoaded
    0.50
    
    0.49
    +:+
    0.48
     CallOverrides
    0.47
     Chwiliwch
    0.44
    ='';
    
    0.42
    EndProject
    0.41
    Activations Density 1.162%

    No Known Activations