© 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. 304
    Prev
    Next
    INDEX
    Explanations

    Programming-related keywords and variable definitions within code

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

    Android Java code and XML layout syntax elements.

    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
    ✭✭
    -0.50
    +#+
    -0.42
    enido
    -0.40
     تسم
    -0.38
    心里
    -0.38
     utafitiHapana
    -0.38
    Beskrivelse
    -0.37
    autorest
    -0.37
    BASELINE
    -0.37
    archiviato
    -0.36
    POSITIVE LOGITS
    LayoutInflater
    1.07
    inflate
    0.89
     onCreateView
    0.87
     Inflate
    0.82
     LayoutInflater
    0.82
     inflate
    0.82
    Infl
    0.79
     inflater
    0.76
     Infl
    0.75
    inflater
    0.71
    Activations Density 0.088%

    No Known Activations