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

    Neuronpedia

    Jacobian LensNEW
    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. 15267
    Prev
    Next
    INDEX
    Explanations

    structured relationships in data tables and comparisons

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

    numbered list items and enumerated sequences, particularly third items in ordered sequences.

    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
    oa̍t
    -0.47
     invokingState
    -0.46
     Exacts
    -0.38
    Aholisi
    -0.37
    :+:
    -0.37
     isInitialized
    -0.35
    ensed
    -0.35
    ORAGE
    -0.34
    blauch
    -0.33
    writeFieldEnd
    -0.33
    POSITIVE LOGITS
     third
    2.50
    third
    2.13
    Third
    2.03
     Third
    1.98
    第三
    1.89
     Thirdly
    1.84
     THIRD
    1.82
     troisième
    1.75
    THIRD
    1.75
     derde
    1.74
    Activations Density 0.898%

    No Known Activations