© 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. 16-GEMMASCOPE-RES-16K
    11. 4842
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or programming syntax

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with 'dy', 'dz'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =[]
    -0.74
    PreferredItem
    -0.71
    "):
    -0.68
     Tew
    -0.68
    jectures
    -0.68
    ribu
    -0.66
    าศ
    -0.66
    [{\
    -0.65
    页面存档备份
    -0.65
    ',
    -0.64
    POSITIVE LOGITS
    FailureListener
    0.66
    .
    0.65
    MLLoader
    0.55
    ;
    0.53
     levure
    0.52
     umane
    0.52
     democrática
    0.49
     ;
    0.49
    PerformLayout
    0.49
     vettoriale
    0.49
    Activations Density 1.585%

    No Known Activations