© 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. 38-GEMMASCOPE-RES-16K
    6. 15282
    Prev
    Next
    INDEX
    Explanations

    terms related to ecosystem services, regulations, and their effects on resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.30
     ISNI
    -0.26
    ❹
    -0.26
    批准
    -0.24
     convidados
    -0.24
     âge
    -0.22
    GMENT
    -0.22
    TextAppearance
    -0.22
     ReSharper
    -0.21
    uscitation
    -0.21
    POSITIVE LOGITS
     services
    3.59
     service
    3.45
     Services
    3.06
    services
    3.00
     Service
    2.95
     SERVICE
    2.92
     SERVICES
    2.92
    service
    2.92
    Services
    2.86
    Service
    2.77
    Activations Density 1.024%

    No Known Activations