© 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. 9756
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms within a context

    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
    UnusedPrivate
    -0.30
    Moder
    -0.28
     manipulate
    -0.27
    ungsbedingungen
    -0.26
    เก็บ
    -0.25
     answered
    -0.25
     wystaw
    -0.25
     weet
    -0.24
    âmara
    -0.24
     perfeitamente
    -0.24
    POSITIVE LOGITS
     disambiguazione
    1.02
     ujednoznacz
    1.00
    rungsseite
    0.82
     utafitiHapana
    0.80
    verwijspagina
    0.71
     Савезне
    0.68
     Vikipedi
    0.68
     Taktlose
    0.66
     يتيمه
    0.65
    homonymie
    0.65
    Activations Density 0.256%

    No Known Activations