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. 10-GEMMASCOPE-RES-16K
    6. 3175
    Prev
    Next
    INDEX
    Explanations

    the presence of names or mentions that include "Van" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -1.09
     bezeichneter
    -0.96
     EconPapers
    -0.92
     bermuda
    -0.91
    )"),
    -0.91
    )});
    -0.87
    })*/
    -0.86
    $)$
    -0.86
     Felicia
    -0.84
    +#+#
    -0.84
    POSITIVE LOGITS
     Van
    1.62
     van
    1.62
     VAN
    1.54
    Van
    1.50
    van
    1.42
     vans
    1.36
    VAN
    1.28
    vans
    1.08
     Vanessa
    1.04
     Vans
    1.02
    Activations Density 0.076%

    No Known Activations