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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 7284
    Prev
    Next
    INDEX
    Explanations

    references to languages and communication skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     correctes
    -0.68
    InSection
    -0.54
    はじめに
    -0.53
    UseVisualStyle
    -0.53
    IntoConstraints
    -0.53
     createState
    -0.50
     Дата
    -0.50
     OkHttpClient
    -0.49
    clientY
    -0.49
    aritions
    -0.49
    POSITIVE LOGITS
     language
    1.36
    language
    1.10
     Language
    1.08
     langage
    1.03
     languages
    1.01
    Language
    1.00
     LANGUAGE
    0.95
     dialect
    0.92
     Sprache
    0.92
     lingua
    0.90
    Activations Density 0.227%

    No Known Activations