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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 10368
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the benefits or advantages of a concept or method

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     catena
    -0.64
    sillon
    -0.64
    }}{\
    -0.63
    zieży
    -0.60
    izumi
    -0.60
    }{\
    -0.60
    }*/
    -0.59
     {\
    -0.58
    letzt
    -0.58
    }`
    -0.57
    POSITIVE LOGITS
     Advantage
    1.61
     advantage
    1.58
    advantage
    1.57
     advantages
    1.54
    Advantage
    1.53
     disadvantage
    1.50
    Advantages
    1.43
     Advantages
    1.43
     disadvantages
    1.42
    ANTAGE
    1.40
    Activations Density 0.105%

    No Known Activations