© 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. 15627
    Prev
    Next
    INDEX
    Explanations

    discussions related to raising children and the challenges associated with parenting

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

    the verb "raise" in contexts involving children, issues, or concerns.

    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
     Kowalski
    -0.39
     Winkel
    -0.38
     utafiti
    -0.35
     Perez
    -0.35
     Solis
    -0.35
     Patton
    -0.35
     Gaspar
    -0.34
    ль
    -0.34
    sweise
    -0.34
     Karp
    -0.34
    POSITIVE LOGITS
     Raise
    1.30
     raising
    1.23
     Raising
    1.23
     raise
    1.22
    Raising
    1.18
    raised
    1.13
     Raised
    1.13
     raised
    1.13
     raises
    1.12
    raising
    1.09
    Activations Density 0.163%

    No Known Activations