© 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. 15853
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms in programming discussions

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

    statements describing problems or issues that occur when running code or applications.

    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
     queſta
    -0.57
    chyma
    -0.53
     desmotivaciones
    -0.53
     shalt
    -0.53
     poffible
    -0.52
     leaſt
    -0.51
    extAlignment
    -0.50
    ましょう
    -0.50
     tričko
    -0.50
     ſche
    -0.49
    POSITIVE LOGITS
     seems
    0.77
     seem
    0.77
     Seems
    0.72
     seemingly
    0.71
     seeming
    0.66
     weirdly
    0.66
     correctly
    0.65
     parece
    0.65
    Seems
    0.65
     strangely
    0.65
    Activations Density 1.030%

    No Known Activations