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. 11902
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court opinions and decisions

    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
    ugo
    -0.40
    빨
    -0.39
    kp
    -0.39
    يكب
    -0.39
    pencer
    -0.38
    DrawerLayout
    -0.38
    筒
    -0.37
    ден
    -0.36
     dí
    -0.36
    
    -0.35
    POSITIVE LOGITS
     majority
    2.36
    majority
    2.18
     Majority
    2.06
    Majority
    1.97
     majorité
    1.74
     Mehrheit
    1.65
     minority
    1.58
     maioria
    1.53
     mayoría
    1.51
     Minority
    1.33
    Activations Density 0.393%

    No Known Activations