© 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. 1703
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to preparation and cooking methods

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

    words and phrases indicating removal, draining, or elimination of excess material.

    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
    TagMode
    -0.46
    UnsafeEnabled
    -0.41
    rungsseite
    -0.41
    uxxxx
    -0.41
     дописавши
    -0.40
     propOrder
    -0.39
     amnesia
    -0.39
    parsedMessage
    -0.39
     transférez
    -0.39
    XmlAccessorType
    -0.39
    POSITIVE LOGITS
     superfluous
    2.19
     excess
    2.13
     unnecessary
    2.09
     surplus
    2.08
     redundant
    1.91
    excess
    1.90
    Excess
    1.88
     Excess
    1.86
     inneces
    1.69
     unused
    1.67
    Activations Density 0.833%

    No Known Activations