© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12233
    Prev
    Next
    INDEX
    Explanations

    keywords related to automotive and gaming industry entities

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

    brands and product lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    InitVars
    -0.71
     cheaply
    -0.60
    CloseOperation
    -0.60
     crappy
    -0.59
     shitty
    -0.56
     booze
    -0.56
    ChildScrollView
    -0.55
     supposedly
    -0.55
     overpriced
    -0.54
     cheap
    -0.54
    POSITIVE LOGITS
     noastre
    0.56
    ®
    0.48
     måte
    0.47
     noastră
    0.44
     conclu
    0.40
    ®-
    0.40
    SequentialGroup
    0.40
     webbplats
    0.40
     freuen
    0.40
     HUAWEI
    0.40
    Activations Density 0.152%

    No Known Activations