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. 14-GEMMASCOPE-RES-16K
    6. 123
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical notation and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maitland
    -0.89
     Saif
    -0.83
     propOrder
    -0.80
     Selva
    -0.80
    ucksack
    -0.79
     Grau
    -0.79
     saites
    -0.78
    MTL
    -0.75
     Simba
    -0.75
     Guilford
    -0.75
    POSITIVE LOGITS
     }^{\
    1.47
    ^{\
    1.33
    )^{\
    1.26
    }^{\
    1.19
    ]^{\
    0.97
     ^{\
    0.95
    }}^{\
    0.91
     }}^{\
    0.90
     $^{\
    0.89
    WriteAttribute
    0.85
    Activations Density 0.208%

    No Known Activations