© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5371
    Prev
    Next
    INDEX
    Explanations

    references to API requests and responses

    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
     blad
    -0.37
     folha
    -0.36
    يكب
    -0.35
     rumput
    -0.34
    <?
    -0.33
     cartilage
    -0.33
    QMetaType
    -0.33
    InputBorder
    -0.33
    olescence
    -0.33
    
    -0.32
    POSITIVE LOGITS
     API
    3.31
     api
    3.02
    API
    2.81
     APIs
    2.63
    api
    2.63
     Api
    2.58
    Api
    2.48
    APIs
    2.09
    APIS
    1.66
    APIC
    1.53
    Activations Density 0.514%

    No Known Activations