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. 11078
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and copyright-related phrases

    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
     ‘
    -0.65
     purpose
    -0.59
     set
    -0.58
     '
    -0.57
    iseks
    -0.57
     inner
    -0.56
    lüğ
    -0.56
     blame
    -0.55
    umumkan
    -0.54
     
    -0.53
    POSITIVE LOGITS
     تضيفلها
    1.00
     typelib
    0.93
    évaluateur
    0.84
    tagHelperRunner
    0.83
    ंदीखरीदारी
    0.81
     nakalista
    0.80
    IndentedString
    0.75
    fillType
    0.74
     gynhyrchwyd
    0.73
    出版年
    0.71
    Activations Density 0.242%

    No Known Activations