© 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. 419
    Prev
    Next
    INDEX
    Explanations

    sentiment and expectations surrounding products or events

    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
     INTERESAR
    -0.43
    ScopeManager
    -0.43
     चीज़ों
    -0.42
     nonUne
    -0.40
     contextLoads
    -0.40
    RectangleBorder
    -0.40
    QMetaType
    -0.38
    @@@@@
    -0.38
    mishes
    -0.37
    دانشنامهٔ
    -0.37
    POSITIVE LOGITS
     deliver
    1.34
     lived
    1.30
     living
    1.26
     delivers
    1.23
     delivering
    1.22
    deliver
    1.22
     delivered
    1.21
     delivery
    1.19
    Deliver
    1.18
     Deliver
    1.17
    Activations Density 0.208%

    No Known Activations