© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    concepts related to space-saving and organization

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

    phrases describing physical space or storage capacity.

    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
     препратки
    -0.46
    tonode
    -0.34
    Хьажоргаш
    -0.32
     haka
    -0.31
     linkovi
    -0.31
     исто
    -0.31
    교
    -0.30
    mtrl
    -0.29
    ssent
    -0.29
     Steffen
    -0.28
    POSITIVE LOGITS
     space
    2.42
    space
    1.98
     espacio
    1.94
     espaço
    1.84
     SPACE
    1.82
     ruimte
    1.80
    Space
    1.79
     Space
    1.77
    空间
    1.73
     spazio
    1.70
    Activations Density 0.351%

    No Known Activations