© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8248
    Prev
    Next
    INDEX
    Explanations

    arguments and perspectives related to equality and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    หน่อย
    -0.56
     Etc
    -0.53
    IsContent
    -0.50
    ellem
    -0.47
     MenuView
    -0.45
    VALIDATE
    -0.45
    页面存档备份
    -0.43
    хьтан
    -0.43
    oredCriteria
    -0.43
    ldre
    -0.42
    POSITIVE LOGITS
     equally
    2.12
     Equally
    1.76
     genauso
    1.64
     altrett
    1.50
     equal
    1.41
     ebenso
    1.34
     igualmente
    1.34
     autant
    1.34
     lika
    1.32
     stejně
    1.31
    Activations Density 0.346%

    No Known Activations