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. 92504
    Prev
    Next
    INDEX
    Explanations

    methods and functions related to string manipulation in code

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

    string conversion methods

    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
     betweenstory
    -0.81
    KommentareTeilen
    -0.75
    $_['
    -0.73
    ########.
    -0.73
     nahilalakip
    -0.70
    
    -0.69
    AddTagHelper
    -0.68
     noDo
    -0.63
     tartalomajánló
    -0.61
     FontWeight
    -0.60
    POSITIVE LOGITS
    toLowerCase
    0.53
    toFloat
    0.52
    toString
    0.46
    tolist
    0.45
    所示
    0.45
    toUpperCase
    0.42
    printStackTrace
    0.41
    toInt
    0.40
    toDouble
    0.40
    .
    0.39
    Activations Density 0.010%

    No Known Activations