© 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. 7761
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and emotional states

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

    first-person present tense statements expressing personal beliefs, opinions, or states of being.

    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
     فريبيس
    -0.64
    MessageTagHelper
    -0.63
    __;
    -0.56
     coff
    -0.55
     Provo
    -0.51
    BagConstraints
    -0.49
     שוליים
    -0.48
    yntaxException
    -0.48
    adaptiveStyles
    -0.46
    点此举报
    -0.46
    POSITIVE LOGITS
     eager
    0.66
     attracted
    0.65
     grateful
    0.65
     wary
    0.65
     keen
    0.65
     convinced
    0.65
     motivated
    0.64
     reluctant
    0.64
     committed
    0.61
     appalled
    0.61
    Activations Density 0.289%

    No Known Activations