© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13708
    Prev
    Next
    INDEX
    Explanations

    requests for validation or corrections regarding information or feelings

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

    expressions of surprise or unexpectedness, particularly words like "surprised" and phrases indicating something is contrary to expectations.

    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
     initComponents
    -0.64
     lccn
    -0.42
    IBOutlet
    -0.41
     iNdEx
    -0.41
     dAtA
    -0.40
    ReusableCell
    -0.40
     yyb
    -0.40
    AutoField
    -0.40
    parametrize
    -0.39
    __":
    -0.39
    POSITIVE LOGITS
     if
    3.36
     если
    2.56
     nếu
    2.38
     jika
    2.36
     dacă
    2.33
     якщо
    2.30
     jeśli
    2.17
     अगर
    2.09
     hvis
    2.09
     اگر
    2.08
    Activations Density 4.536%

    No Known Activations