© 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. 6-GEMMASCOPE-RES-16K
    11. 13751
    Prev
    Next
    INDEX
    Explanations

    terms related to rarity and exceptional cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelState
    -0.65
    บาย
    -0.64
     allemaal
    -0.56
    PhysRevD
    -0.56
     springfox
    -0.56
     esternos
    -0.55
    ikkert
    -0.53
    ListNode
    -0.52
    asiest
    -0.51
     instantaneously
    -0.51
    POSITIVE LOGITS
     rare
    1.37
     rarer
    1.22
    Rare
    1.20
     Rare
    1.20
    rare
    1.17
     rarity
    1.14
     rares
    1.05
     RARE
    1.04
     rarest
    1.03
     Rarely
    0.87
    Activations Density 0.266%

    No Known Activations