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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1806
    Prev
    Next
    INDEX
    Explanations

    references to programs, projects, and their operational aspects

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

    the phrase "get it to work" or similar expressions about making something functional.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     geweest
    -0.29
    eschön
    -0.28
     valable
    -0.27
     есте
    -0.27
    difficulty
    -0.27
    
    -0.27
    CYAN
    -0.27
     انتظار
    -0.27
     chrétienne
    -0.27
    Unexpected
    -0.26
    POSITIVE LOGITS
     sorted
    0.69
     positioned
    0.68
     repaired
    0.67
     hooked
    0.66
     restored
    0.66
    /**
    0.65
     rescheduled
    0.64
     locked
    0.64
     reinstated
    0.64
     nerfed
    0.63
    Activations Density 0.130%

    No Known Activations