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. 107890
    Prev
    Next
    INDEX
    Explanations

    phrases expressing certainty or shared knowledge

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

    as we know it

    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
     otomatig
    -0.34
     péro
    -0.30
    //
    -0.29
    térature
    -0.28
    לית
    -0.28
    évaluateur
    -0.27
    titem
    -0.27
    wußt
    -0.27
     injection
    -0.26
    ęt
    -0.26
    POSITIVE LOGITS
     disambiguazione
    0.71
    :✨
    0.63
     pinulongan
    0.62
     recognizable
    0.58
     recognisable
    0.58
    Personendaten
    0.57
     familiar
    0.57
     Elsewhere
    0.54
     Wicidata
    0.54
     conocemos
    0.54
    Activations Density 0.014%

    No Known Activations