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. 56773
    Prev
    Next
    INDEX
    Explanations

    terms related to HTTP client implementation in programming

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

    client network clients

    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
    RetentionPolicy
    -0.68
     Administrativna
    -0.55
    #+#
    -0.54
    ьаж
    -0.53
    $_['
    -0.50
     ModelExpression
    -0.50
     SqlParameter
    -0.50
    lapsingToolbar
    -0.49
    setVerticalGroup
    -0.49
     onCreateView
    -0.48
    POSITIVE LOGITS
    OkHttpClient
    0.61
     OkHttpClient
    0.43
    HttpClient
    0.42
    trading
    0.40
     informée
    0.39
    Bronnen
    0.38
     flota
    0.36
     institucional
    0.35
    ExecutorService
    0.35
     électroniques
    0.34
    Activations Density 0.008%

    No Known Activations