© 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. 3-GEMMASCOPE-RES-16K
    11. 7144
    Prev
    Next
    INDEX
    Explanations

    references to various forms of collapse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.62
    twimg
    -0.61
    Portail
    -0.59
     scre
    -0.58
    {\
    -0.57
    蒙
    -0.55
     interceptor
    -0.55
    Sno
    -0.55
    แ
    -0.54
     latar
    -0.54
    POSITIVE LOGITS
     collapse
    2.42
    collapse
    2.19
     Collapse
    2.17
     collapses
    2.01
    Collapse
    1.87
     collapsing
    1.82
     collapsed
    1.81
    lapsing
    1.49
    collapsed
    1.40
    Collapsed
    1.26
    Activations Density 0.146%

    No Known Activations