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. 108389
    Prev
    Next
    INDEX
    Explanations

    references to hash code functions in programming contexts

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

    hashCode method calls

    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
    
    -0.46
    ⓘ
    -0.45
    ttino
    -0.45
    
    -0.45
    ETT
    -0.42
     Sill
    -0.41
     Ped
    -0.41
    zzi
    -0.40
    illot
    -0.40
     Cock
    -0.40
    POSITIVE LOGITS
     hashCode
    2.81
    hashCode
    1.40
    HashCode
    1.27
    GetHashCode
    0.88
    Autoritní
    0.63
    VersionUID
    0.62
     getItemId
    0.58
     hash
    0.57
     OFDb
    0.54
    OGND
    0.52
    Activations Density 0.002%

    No Known Activations