© 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. 15-GEMMASCOPE-RES-16K
    6. 8491
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    -0.54
    del
    -0.47
    Ef
    -0.45
     had
    -0.45
    if
    -0.42
    спита
    -0.42
    int
    -0.42
     واحدة
    -0.41
    gin
    -0.41
     something
    -0.41
    POSITIVE LOGITS
    adaptiveStyles
    0.93
    IntoConstraints
    0.87
    WebElementEntity
    0.86
    AutoresizingMask
    0.85
    }))
    
    0.83
    saraba
    0.81
     insuffisamment
    0.80
    ])):
    0.79
    Достоинства
    0.78
    ]--;
    0.77
    Activations Density 0.382%

    No Known Activations