© 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. 10-GEMMASCOPE-RES-16K
    6. 4134
    Prev
    Next
    INDEX
    Explanations

    legal terms and citations

    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
    ніципа
    -0.67
     acorns
    -0.64
    thâu
    -0.56
     față
    -0.55
     Apare
    -0.55
     raisins
    -0.54
     Guilherme
    -0.53
     convulsions
    -0.53
     Utt
    -0.52
     yoox
    -0.51
    POSITIVE LOGITS
    TabIndex
    6.29
    AndEndTag
    1.14
    ScopeManager
    1.12
     AssemblyTitle
    1.05
     consultato
    1.04
     CreateTagHelper
    1.03
     مشين
    1.01
    DockStyle
    0.99
    脚注の使い方
    0.98
    twimg
    0.94
    Activations Density 0.007%

    No Known Activations