© 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. 10-GEMMASCOPE-RES-16K
    11. 12462
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases emphasizing reiteration or emphasis in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sune
    -0.56
    chau
    -0.51
    blatt
    -0.49
    documentclass
    -0.48
     par
    -0.47
    gabung
    -0.47
     hẳn
    -0.47
    cephalus
    -0.46
     similarly
    -0.46
    TagHelper
    -0.46
    POSITIVE LOGITS
    HasForeignKey
    0.78
    AxisAlignment
    0.72
    UIControlState
    0.64
    دانشنامهٔ
    0.62
    KommentareTeilen
    0.62
    makeConstraints
    0.61
    awtextra
    0.61
     صوتيه
    0.60
     esportivo
    0.59
     orgánica
    0.58
    Activations Density 0.230%

    No Known Activations