© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 804
    Prev
    Next
    INDEX
    Explanations

    terms related to decision-making and organizational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.05
     Monfieur
    -0.96
    RUnlock
    -0.92
    StoryboardSegue
    -0.91
     becauſe
    -0.87
     dourada
    -0.87
     Jefus
    -0.87
    ^(@)
    -0.86
     purpoſe
    -0.83
     houſe
    -0.82
    POSITIVE LOGITS
     censo
    0.46
    WithIOException
    0.45
     Brooklyn
    0.43
     Connecticut
    0.43
    ьаж
    0.42
     кру
    0.41
    Шаг
    0.40
     berta
    0.39
    iato
    0.39
    bian
    0.38
    Activations Density 1.283%

    No Known Activations