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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 122396
    Prev
    Next
    INDEX
    Explanations

    references to hashing and hash-related functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    enumii
    -0.69
     BrowserModule
    -0.65
     للاسماء
    -0.65
    WEBPACK
    -0.59
    BrowserModule
    -0.58
    PreferredItem
    -0.57
    XmlAccessType
    -0.56
     UIP
    -0.55
     للمعارف
    -0.54
    __":
    
    -0.54
    POSITIVE LOGITS
     hash
    1.31
     Hash
    1.24
    hash
    1.21
    Hash
    1.21
     HASH
    1.10
    HASH
    1.08
     hashing
    0.98
     hashes
    0.92
    hashes
    0.91
    Hashes
    0.88
    Activations Density 0.008%

    No Known Activations