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. 5-GEMMASCOPE-RES-16K
    6. 6173
    Prev
    Next
    INDEX
    Explanations

    instances of the word "multi" and related phrases indicating multiple characteristics or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     végétale
    -0.73
     japonais
    -0.73
    اریخ
    -0.72
     grecque
    -0.70
     referrerpolicy
    -0.70
     artesanales
    -0.70
     veneta
    -0.69
     préalable
    -0.69
    étique
    -0.68
    })`
    -0.68
    POSITIVE LOGITS
     multi
    2.17
     Multi
    2.17
    multi
    2.10
    Multi
    2.03
     MULTI
    1.75
     MULT
    1.73
    MULT
    1.72
    MULTI
    1.65
     multilayer
    1.34
     multic
    1.26
    Activations Density 0.099%

    No Known Activations