© 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. 3783
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries

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

    question words and interrogative sentence structures.

    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
     they
    -0.58
    ThroughAttribute
    -0.54
     estekak
    -0.52
     ujednoznacz
    -0.52
    ✭✭
    -0.51
     يتيمه
    -0.49
     MainAxisSize
    -0.49
     kasarigan
    -0.48
    ➋
    -0.47
    /*++
    -0.46
    POSITIVE LOGITS
     does
    1.31
     did
    1.23
     do
    1.20
    Does
    0.86
     Does
    0.85
     Did
    0.85
    does
    0.84
    Did
    0.83
     are
    0.82
    did
    0.80
    Activations Density 0.181%

    No Known Activations