© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13225
    Prev
    Next
    INDEX
    Explanations

    financial values and metrics related to revenue or gains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zydent
    -0.51
    曖昧さ回避
    -0.49
     reale
    -0.49
    خاذ
    -0.48
    了一种
    -0.48
    cektir
    -0.46
    %@",
    -0.46
    ৌ
    -0.44
    ண்டும்
    -0.44
    っており
    -0.43
    POSITIVE LOGITS
    ########.
    0.86
    enumi
    0.77
     beginnetje
    0.76
     CreateTagHelper
    0.74
     Füße
    0.71
     ویکی‌پدیای
    0.70
    mybatisplus
    0.69
     Roskov
    0.68
    expandindo
    0.68
    elemField
    0.68
    Activations Density 0.298%

    No Known Activations