© 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. 11121
    Prev
    Next
    INDEX
    Explanations

    phrases expressing economic motivations and business dynamics

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

    sequences describing causality or logical connections between actions and their outcomes or purposes.

    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
    蚪
    -0.47
     nakalista
    -0.46
    告诉我
    -0.44
    Datuak
    -0.40
     gawas
    -0.40
    ømme
    -0.39
     vastaan
    -0.38
    Fach
    -0.37
    copg
    -0.36
     interpretación
    -0.36
    POSITIVE LOGITS
     benefit
    0.88
     benefiting
    0.85
     helping
    0.76
     bless
    0.74
    benefit
    0.71
     Helping
    0.69
    Helping
    0.67
     Benefit
    0.66
     protect
    0.65
    帮助
    0.65
    Activations Density 0.697%

    No Known Activations