© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10709
    Prev
    Next
    INDEX
    Explanations

    terms related to record-keeping and registries, particularly in legal and health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pat
    -0.32
     کاب
    -0.31
    Seek
    -0.30
     WANT
    -0.30
     तर
    -0.29
    seek
    -0.28
    LookAnd
    -0.28
     Paglinawan
    -0.28
    TRANSLATE
    -0.28
    OrNil
    -0.28
    POSITIVE LOGITS
     records
    0.78
     registers
    0.68
     registry
    0.66
     register
    0.65
     databases
    0.63
     database
    0.63
    Hentet
    0.61
     Normdatei
    0.59
     Records
    0.59
     témoig
    0.58
    Activations Density 0.247%

    No Known Activations