© 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. 21-GEMMASCOPE-RES-16K
    11. 8064
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and operators

    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
     autorytatywna
    -0.88
    istoitu
    -0.81
     ModelExpression
    -0.77
    kháu
    -0.75
    AutoScaleMode
    -0.72
    исленность
    -0.70
     архивлан
    -0.69
    Tikang
    -0.68
     שוליים
    -0.66
     <=",
    -0.65
    POSITIVE LOGITS
     의
    0.51
     로
    0.49
     )
    0.49
     的
    0.44
     를
    0.43
     에
    0.43
     hígado
    0.42
     。
    0.41
     );
    0.41
     ]
    0.41
    Activations Density 0.219%

    No Known Activations