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. 1-GEMMASCOPE-RES-16K
    6. 5804
    Prev
    Next
    INDEX
    Explanations

    Mathematical operators and symbols indicating numerical relationships or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیای
    -0.72
     inversa
    -0.61
    omeness
    -0.59
    )_/¯
    -0.59
    ிறது
    -0.54
     heen
    -0.54
    Vanjske
    -0.54
     Gegenteil
    -0.52
    而成
    -0.51
    NEYS
    -0.51
    POSITIVE LOGITS
    >+</
    1.48
    }+
    1.39
    )+\
    1.33
    +\
    1.27
    }+\
    1.27
    )+
    1.26
    +
    1.16
    )}+\
    1.10
    )}+
    1.06
    }}+\
    1.06
    Activations Density 0.540%

    No Known Activations