© 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. 4653
    Prev
    Next
    INDEX
    Explanations

    food-related terms and descriptions

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

    specific food dishes and their names.

    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
    лтемелер
    -0.45
     HttpNotFound
    -0.43
     パスタ
    -0.43
     ябло
    -0.43
     Chardonnay
    -0.42
    #+#
    -0.42
     cabo
    -0.40
     cheddar
    -0.39
     Renoir
    -0.39
    パスタ
    -0.39
    POSITIVE LOGITS
     stall
    0.52
     stalls
    0.48
     delicacies
    0.46
     segredo
    0.44
    躇
    0.44
    StructEnd
    0.43
    Muslim
    0.43
    BufferException
    0.42
    Authentic
    0.42
     boiled
    0.41
    Activations Density 0.253%

    No Known Activations