© 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. 8-GEMMASCOPE-RES-16K
    11. 15362
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to contradiction and opposition 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 @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.60
     religieuses
    -0.55
    petito
    -0.53
     équip
    -0.51
     iNdEx
    -0.51
     barato
    -0.51
     οποία
    -0.51
    存于互联网档案馆
    -0.50
    Namaste
    -0.50
     tartalomajánló
    -0.50
    POSITIVE LOGITS
    ImageContext
    0.65
    kään
    0.64
    :✨
    0.60
    følgelig
    0.59
    ríklad
    0.57
    xase
    0.57
    localctx
    0.57
    smithy
    0.57
    Composable
    0.55
    mbggenerated
    0.55
    Activations Density 0.746%

    No Known Activations