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. 23-GEMMASCOPE-RES-131K
    6. 23155
    Prev
    Next
    INDEX
    Explanations

    keywords related to hashing functions and hash codes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.64
     BrowserModule
    -0.59
    TemporalType
    -0.56
     للاسماء
    -0.54
     للمعارف
    -0.53
    endcsname
    -0.52
    WEBPACK
    -0.52
    PRNewswire
    -0.51
    ⤒
    -0.50
    SpringRunner
    -0.50
    POSITIVE LOGITS
     hash
    1.23
     Hash
    1.17
    Hash
    1.14
    hash
    1.13
    HASH
    1.09
     HASH
    1.06
     hashing
    0.94
     hashes
    0.89
    hashes
    0.88
    Hashes
    0.81
    Activations Density 0.006%

    No Known Activations