© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104565
    Prev
    Next
    INDEX
    Explanations

    occurrences of objects or entities being stuck or immobilized in various contexts

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

    Words describing impediments to movement, progress, or function, often indicating that something has been stopped, slowed, or constrained from its normal operation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     short
    -0.38
     것이다
    -0.36
    short
    -0.35
     loss
    -0.34
    loss
    -0.34
    verlust
    -0.34
    Loss
    -0.33
     αλ
    -0.31
    subpackage
    -0.31
     Loss
    -0.31
    POSITIVE LOGITS
     stalled
    0.79
     halted
    0.77
     stalemate
    0.75
     Stuck
    0.74
     froze
    0.73
     stuck
    0.73
     blockade
    0.72
     propOrder
    0.71
     halting
    0.70
     paralyzed
    0.69
    Activations Density 0.180%

    No Known Activations