© 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. 5906
    Prev
    Next
    INDEX
    Explanations

    numeric patterns and mathematical expressions

    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
     surla
    -0.60
    BASELINE
    -0.56
    ColumnHeaders
    -0.51
    Rightarrow
    -0.49
     EDR
    -0.48
    U
    -0.48
    اتها
    -0.47
     başına
    -0.47
     tragically
    -0.46
    اته
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    0.70
    لينكات
    0.65
    Hozzáférés
    0.61
     resourceCulture
    0.60
     MainAxisSize
    0.59
    رشف
    0.59
    AndEndTag
    0.58
    цездатний
    0.57
    ureux
    0.56
    PropertyChanging
    0.55
    Activations Density 0.969%

    No Known Activations