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. 24-GEMMASCOPE-RES-131K
    6. 1205
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to financial management and investment strategies

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

    managing projects and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.51
     intptr
    -0.44
     fuck
    -0.43
     față
    -0.42
     fucks
    -0.41
     ویکی‌پدی
    -0.40
    Yet
    -0.40
     Verhält
    -0.38
     مشين
    -0.38
     Pourtant
    -0.38
    POSITIVE LOGITS
    WaitGroup
    0.60
    adpleegd
    0.55
     among
    0.47
     rédaction
    0.47
     kasama
    0.46
    ImageContext
    0.46
     iprot
    0.46
    bleshooting
    0.46
    Datuak
    0.44
     příslu
    0.44
    Activations Density 0.035%

    No Known Activations