© 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. 1-GEMMASCOPE-RES-16K
    11. 14738
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "up" and "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '{@
    -0.71
    RectangleBorder
    -0.68
     كومونز
    -0.64
    ParallelGroup
    -0.60
     Theſe
    -0.60
    KommentareTeilen
    -0.56
     modelli
    -0.54
     slowest
    -0.52
    ettbewer
    -0.52
    Rüyada
    -0.52
    POSITIVE LOGITS
    adaptiveStyles
    0.64
    cyklopedia
    0.59
    rxjs
    0.57
    SpringBootTest
    0.53
    RetentionPolicy
    0.52
    LabelTagHelper
    0.52
    utnik
    0.51
     تضيفلها
    0.50
     Parenthood
    0.49
    Einzelnachweise
    0.49
    Activations Density 0.768%

    No Known Activations