© 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. 2638
    Prev
    Next
    INDEX
    Explanations

    locations and addresses related to professional services

    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
     kasarigan
    -0.77
     JpaRepository
    -0.51
     للمعارف
    -0.48
    angkan
    -0.48
     insuffisamment
    -0.46
     ioe
    -0.45
    ització
    -0.45
     façons
    -0.45
     SUDOC
    -0.45
     TableColumn
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.77
     betweenstory
    0.62
     divisible
    0.56
    EDEFAULT
    0.55
     BrowserModule
    0.55
    setof
    0.54
    PointerException
    0.54
     dieß
    0.53
    Tembelea
    0.53
     صوتيه
    0.53
    Activations Density 0.104%

    No Known Activations