© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2187
    Prev
    Next
    INDEX
    Explanations

    relationships between companies and their collaborations or competition, particularly in a technological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gatsby
    -0.48
     Савезне
    -0.47
    RTLD
    -0.47
    ankan
    -0.47
     opérateur
    -0.47
    štění
    -0.45
    юр
    -0.43
     [*]
    -0.42
     Legendre
    -0.42
    ensation
    -0.41
    POSITIVE LOGITS
     battle
    2.57
     fight
    2.38
     battles
    2.22
    battle
    2.12
    fight
    2.02
     fights
    1.98
     fighting
    1.97
     battled
    1.96
     fought
    1.95
     battling
    1.93
    Activations Density 0.452%

    No Known Activations