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. 21-GEMMASCOPE-RES-16K
    6. 15104
    Prev
    Next
    INDEX
    Explanations

    references to missions or the act of evangelizing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.55
    DebuggerStep
    -0.53
    getline
    -0.51
     Toibin
    -0.49
    Personendaten
    -0.48
    vima
    -0.47
    })*/
    -0.47
    tainty
    -0.45
    hoeddwyd
    -0.45
    ksy
    -0.45
    POSITIVE LOGITS
     mission
    1.13
     missions
    1.11
     missionary
    1.03
     spreading
    1.03
    mission
    1.01
     Mission
    1.00
    Mission
    0.99
     spread
    0.98
     missione
    0.97
     Missions
    0.96
    Activations Density 0.096%

    No Known Activations