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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6169
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to causal relationships and logical conclusions

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

    Text preceding em dashes or "hence"

    np_acts-logits-general · gemini-2.0-flash

    concluding statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -1.07
     Infórmanos
    -0.85
    🔥🔥
    -0.73
    性
    -0.69
     _____
    -0.69
     —
    -0.68
     ....
    -0.68
    ualmente
    -0.67
    ally
    -0.67
    unknownFields
    -0.67
    POSITIVE LOGITS
    ––––
    1.40
     –
    1.05
     
    1.02
     ​​
    1.01
    ţilor
    0.99
    ––
    0.98
    ায়
    0.97
    ര്‍
    0.96
    ്‍
    0.94
    ţii
    0.92
    Activations Density 0.565%

    No Known Activations