© 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. 14003
    Prev
    Next
    INDEX
    Explanations

    elements related to programming, particularly with a focus on object properties and method definitions

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

    identifier or property names ending in "Id" that refer to database records or object attributes.

    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
    InputChange
    -0.45
    transQ
    -0.41
    Ine
    -0.41
    Inches
    -0.40
     Lance
    -0.40
     insuffisamment
    -0.40
    Brainz
    -0.39
    faux
    -0.39
    unix
    -0.39
    InBytes
    -0.39
    POSITIVE LOGITS
     id
    0.86
    id
    0.75
    setId
    0.64
     ID
    0.63
    Id
    0.61
    Vidite
    0.57
    getId
    0.56
    idler
    0.56
     identidad
    0.56
    idity
    0.55
    Activations Density 0.100%

    No Known Activations