© 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. 3-GEMMASCOPE-RES-16K
    11. 5872
    Prev
    Next
    INDEX
    Explanations

    terminology related to locking mechanisms or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.80
     humaine
    -0.76
     bakgrund
    -0.75
     réaliste
    -0.74
     calitate
    -0.74
     flesta
    -0.73
     rendus
    -0.73
     tilbage
    -0.72
     esempi
    -0.71
     gră
    -0.71
    POSITIVE LOGITS
     lock
    3.29
     Lock
    3.09
    lock
    3.02
     LOCK
    3.02
     locks
    2.96
    Lock
    2.82
    LOCK
    2.76
     Locks
    2.68
     locked
    2.64
    locks
    2.60
    Activations Density 0.040%

    No Known Activations