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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4221
    Prev
    Next
    INDEX
    Explanations

    expressions of affection or positivity towards items, particularly in the context of personal belongings or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ActivatedRoute
    -0.50
    PMailer
    -0.49
    orianCalendar
    -0.47
     SDLK
    -0.45
     fiscale
    -0.44
     pymongo
    -0.44
    Liefs
    -0.43
     vettoriale
    -0.43
     cabelos
    -0.42
    onViewCreated
    -0.42
    POSITIVE LOGITS
     adjustable
    0.93
     collapsible
    0.93
     reusable
    0.90
     waterproof
    0.88
     silicone
    0.88
     foldable
    0.84
     washable
    0.84
     inexpensive
    0.83
     nylon
    0.82
     ergonom
    0.81
    Activations Density 0.527%

    No Known Activations