© 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. 30-GEMMASCOPE-RES-16K
    11. 10742
    Prev
    Next
    INDEX
    Explanations

    references to sensory perception and experiences

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

    Referring to the senses

    np_acts-logits-general · gemini-2.0-flash

    sensory input and experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.42
    mybatisplus
    -0.37
     beginnetje
    -0.35
    sidemargin
    -0.31
     Trotz
    -0.31
     sost
    -0.30
     StringTokenizer
    -0.30
     stamped
    -0.30
     intptr
    -0.29
     deuda
    -0.29
    POSITIVE LOGITS
     sensory
    1.60
     senses
    1.57
    sensory
    1.38
     Sensory
    1.37
    Sensory
    1.34
     Senses
    1.32
     sensorial
    1.29
     sentidos
    1.10
     sense
    1.08
     sensor
    1.07
    Activations Density 0.259%

    No Known Activations