© 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. 11767
    Prev
    Next
    INDEX
    Explanations

    ownership and possession in context

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

    the verb "have" followed by a past participle, indicating present perfect tense constructions.

    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
     arşivlendi
    -0.37
    IVEREF
    -0.37
    ย์
    -0.35
     trámite
    -0.33
     perfons
    -0.33
     toiminta
    -0.33
    ėse
    -0.33
     interesar
    -0.32
     elämä
    -0.32
    ępnie
    -0.32
    POSITIVE LOGITS
     different
    0.62
     already
    0.55
     now
    0.54
     been
    0.52
    different
    0.51
    rema
    0.50
     always
    0.49
    endon
    0.49
     got
    0.49
     certain
    0.48
    Activations Density 0.250%

    No Known Activations