© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2152
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to algorithms and programming, particularly focused on database operations and error handling

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

    compound nouns or noun phrases where a modifier precedes the main noun.

    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
     probably
    -0.74
     certainly
    -0.70
    probably
    -0.66
    certainly
    -0.65
     Probably
    -0.61
     certainement
    -0.59
     tentu
    -0.59
    Probably
    -0.59
     often
    -0.59
     usually
    -0.58
    POSITIVE LOGITS
     вдруг
    0.77
     fails
    0.74
     yoksa
    0.68
     jemals
    0.64
     exceeds
    0.64
     blijkt
    0.61
     forem
    0.60
     decides
    0.59
     initComponents
    0.59
     alguno
    0.59
    Activations Density 0.835%

    No Known Activations