© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal and emotional devotion or attachment

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

    periods and commas that end sentences or clauses.

    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
     indígen
    -0.65
     dieſe
    -0.52
    nEnter
    -0.51
     quelcon
    -0.50
    chaffen
    -0.50
    icitis
    -0.50
     desmotivaciones
    -0.49
     plufieurs
    -0.49
    Dichloroethene
    -0.49
     increí
    -0.49
    POSITIVE LOGITS
    这位
    0.71
    這位
    0.62
    SequentialGroup
    0.42
    veter
    0.41
    optionalTypeArgs
    0.40
    Sc
    0.40
     jeune
    0.39
     him
    0.39
    ValueStyle
    0.38
    Former
    0.37
    Activations Density 0.177%

    No Known Activations