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. 19-GEMMASCOPE-RES-16K
    6. 15809
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to legal cases and individuals involved in them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.76
    tonode
    -0.71
    月号
    -0.71
    الحياه
    -0.70
    ISupport
    -0.70
    didSet
    -0.69
     pinulongan
    -0.69
    Хьажоргаш
    -0.67
    ❹
    -0.67
     kasarigan
    -0.67
    POSITIVE LOGITS
     sandero
    0.48
     houſe
    0.47
    BrowserModule
    0.47
    RTEE
    0.46
     Klä
    0.45
     InputDecoration
    0.45
    typec
    0.45
     Vgl
    0.44
     χρόν
    0.43
     segn
    0.42
    Activations Density 2.215%

    No Known Activations