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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 35612
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places

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

    names with international origins

    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
    ViewFeatures
    -0.56
    WithIdentifier
    -0.51
    -------
    -0.49
     оба
    -0.47
     aliment
    -0.46
    phosa
    -0.46
     Wikimedijinoj
    -0.42
     Faso
    -0.42
    styleable
    -0.41
    TypedDataSet
    -0.41
    POSITIVE LOGITS
    `{.
    0.50
    IVEREF
    0.48
    __':
    
    0.44
    Spect
    0.42
    reportWebVitals
    0.42
    thodon
    0.42
     Nguy
    0.42
     pyplot
    0.41
    <?
    0.41
    opatho
    0.41
    Activations Density 0.076%

    No Known Activations