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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8613
    Prev
    Next
    INDEX
    Explanations

    references to languages and their use

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

    Mentioning languages or language skills

    np_acts-logits-general · gemini-2.0-flash

    languages spoken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.75
    astify
    -0.65
    IntoConstraints
    -0.64
    CardHeader
    -0.62
    multer
    -0.54
     Kitts
    -0.53
     kaynağından
    -0.52
    UnitTesting
    -0.52
    Rptr
    -0.51
    Personensuche
    -0.50
    POSITIVE LOGITS
     languages
    2.03
     language
    1.96
     Language
    1.72
    Language
    1.71
     Languages
    1.69
    language
    1.67
    Languages
    1.61
     English
    1.58
     LANGUAGE
    1.54
     lingua
    1.51
    Activations Density 0.357%

    No Known Activations