Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24302
    Prev
    Next
    INDEX
    Explanations

    instances of the word "collapse" and its variations

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

    collapse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
     Савезне
    -0.59
    ьаж
    -0.49
     SwitchCompat
    -0.47
    AndEndTag
    -0.46
     surla
    -0.43
    liceerd
    -0.41
     ویکی‌پدی
    -0.40
    JspWriter
    -0.40
    ruptedException
    -0.39
    POSITIVE LOGITS
    Collapse
    0.78
     collapse
    0.75
    collapse
    0.75
     Collapse
    0.71
     collapsed
    0.67
     collapses
    0.64
     caída
    0.61
     collapsing
    0.60
    collapsed
    0.57
    塌
    0.56
    Activations Density 0.009%

    No Known Activations