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. 11-GEMMASCOPE-RES-16K
    6. 1959
    Prev
    Next
    INDEX
    Explanations

    references to diverse client groups, particularly in social or dining contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.58
    giveness
    -0.58
    jutnya
    -0.57
     AssemblyCulture
    -0.56
    plier
    -0.55
    setVerticalGroup
    -0.55
    czegóły
    -0.55
    [*
    -0.54
    Filmographie
    -0.54
    transQ
    -0.54
    POSITIVE LOGITS
    مراجع
    0.62
    المراجع
    0.60
    mybatisplus
    0.58
     clientèle
    0.57
     customers
    0.55
     BoxDecoration
    0.55
     considérons
    0.53
    zień
    0.52
    naies
    0.50
     customer
    0.49
    Activations Density 0.223%

    No Known Activations