© 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. 31-GEMMASCOPE-RES-16K
    11. 1310
    Prev
    Next
    INDEX
    Explanations

    phrases and descriptors related to food quality and enjoyment

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

    positive evaluative phrases describing food and experiences as delicious or satisfying.

    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
    เหร
    -0.43
    (!__
    -0.43
    ImageContext
    -0.42
    以此
    -0.38
     تكبرها
    -0.38
    InitVars
    -0.38
     nakalista
    -0.36
    ésultat
    -0.36
    这是一
    -0.36
    +#+
    -0.36
    POSITIVE LOGITS
     peccato
    0.64
     comparable
    0.63
     especially
    0.62
    comparable
    0.62
    better
    0.62
     better
    0.61
    unlike
    0.61
     even
    0.60
    especially
    0.59
     BoxFit
    0.57
    Activations Density 0.304%

    No Known Activations