© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 55691
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the taste quality of food

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

    taste or food quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     judgment
    -0.51
     enf
    -0.47
     judgement
    -0.44
     sense
    -0.44
     vů
    -0.44
     Chambre
    -0.42
    hoenix
    -0.42
     corrispond
    -0.42
     commission
    -0.41
     belief
    -0.41
    POSITIVE LOGITS
     tasty
    1.86
     Tasty
    1.66
    tasty
    1.64
    Tasty
    1.63
     yummy
    1.07
     lecker
    0.91
     Yummy
    0.86
    Yummy
    0.84
     flavorful
    0.80
     delectable
    0.76
    Activations Density 0.002%

    No Known Activations