© 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. 5-GEMMASCOPE-RES-16K
    11. 863
    Prev
    Next
    INDEX
    Explanations

    terms related to expulsion and being forced out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prés
    -0.54
     endeavour
    -0.46
    cgi
    -0.46
    requent
    -0.45
    от
    -0.44
     تماس
    -0.44
     bekle
    -0.43
     endeavours
    -0.43
    ↵↵
    -0.43
     endeavor
    -0.42
    POSITIVE LOGITS
     expulsion
    1.25
     eviction
    1.19
     evicted
    1.17
     expelled
    1.17
     expuls
    1.10
     expel
    1.01
     ejected
    0.95
     banished
    0.92
     ousted
    0.92
     ejection
    0.91
    Activations Density 0.294%

    No Known Activations