Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 7310
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables associated with formal definitions and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or algebraic notation

    np_acts-logits-general · gemini-2.0-flash

    archaic spellings of names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.71
    }$_
    -0.61
    </sub>
    -0.58
     "
    -0.58
    <eos>
    -0.56
     })}
    -0.56
     }}}
    -0.54
    ↵↵
    -0.52
     -->
    
    -0.52
     $_{
    -0.51
    POSITIVE LOGITS
     Monfieur
    1.15
     Efq
    1.03
     Cæsar
    1.00
     myſelf
    0.98
     himſelf
    0.97
     Jefus
    0.95
     Majefty
    0.89
     uſed
    0.89
     Anſ
    0.89
     leaſt
    0.84
    Activations Density 7.201%

    No Known Activations