© 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. 15759
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and moments of reflection

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

    phrases describing physical exhaustion, breathing difficulty, or recovery from exertion.

    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
    Erreferentziak
    -0.51
    jsdelivr
    -0.47
     BoxFit
    -0.43
    脚注の使い方
    -0.43
    Източници
    -0.42
    ⮕
    -0.39
     actionMode
    -0.38
    Бележки
    -0.36
     pinulongan
    -0.35
     requête
    -0.35
    POSITIVE LOGITS
     recover
    1.26
     recovers
    1.23
     recuper
    1.20
     recovering
    1.16
     recovery
    1.16
    recover
    1.09
     Recover
    1.08
     recovered
    1.05
     Recovery
    1.02
     stabilize
    1.02
    Activations Density 0.327%

    No Known Activations