Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 16302
    Prev
    Next
    INDEX
    Explanations

    distinctive numerical values or references to specific measurements

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

    Code, names, or copyright information

    np_acts-logits-general · gemini-2.0-flash

    looks like, compares

    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
    存于互联网档案馆
    -0.85
    mybatisplus
    -0.85
     propOrder
    -0.82
    ſelf
    -0.81
    nonatomic
    -0.76
     endometriosis
    -0.76
    Parcelize
    -0.74
    enderror
    -0.74
     themſelves
    -0.74
    tiérrez
    -0.72
    POSITIVE LOGITS
     looks
    0.78
    Looks
    0.71
     Looks
    0.68
    looks
    0.65
     dirait
    0.62
    compare
    0.62
     ressemb
    0.61
    Compare
    0.60
     look
    0.59
     Notice
    0.57
    Activations Density 0.221%

    No Known Activations