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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56593
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "retrieve" and its variations in various forms

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

    retrieving data or items

    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
     imagePath
    -0.60
     newNode
    -0.59
     setPrice
    -0.59
     صوتيه
    -0.58
     Knopf
    -0.58
    Kos
    -0.58
     packageName
    -0.58
     newName
    -0.57
     categoryId
    -0.57
     companyId
    -0.57
    POSITIVE LOGITS
     retrieve
    0.95
    retrieve
    0.94
     Retrieve
    0.94
    Retrieve
    0.93
     retrieval
    0.88
     retrieved
    0.83
     Retrieval
    0.79
     retrieving
    0.76
     recuperação
    0.71
    Retrieval
    0.69
    Activations Density 0.004%

    No Known Activations