© 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. 33-GEMMASCOPE-RES-16K
    11. 1308
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the condition and status of products, particularly related to their packaging and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    học
    -0.35
    ChrTalk
    -0.34
    Personendaten
    -0.33
     inconvénients
    -0.31
     évi
    -0.30
    เกี่ยว
    -0.30
     başlad
    -0.30
    sipasi
    -0.30
    brainly
    -0.29
     dovol
    -0.29
    POSITIVE LOGITS
     condition
    1.61
    condition
    1.42
     Condition
    1.35
    Condition
    1.31
     CONDITION
    1.26
    CONDITION
    1.17
     pristine
    1.02
     kondisi
    0.98
     undamaged
    0.98
     intact
    0.93
    Activations Density 0.153%

    No Known Activations