Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 3166
    Prev
    Next
    INDEX
    Explanations

    terms related to API requests and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.79
    ViewInit
    -0.75
    AfterClass
    -0.74
    findpost
    -0.74
    viewDidLoad
    -0.68
    ########.
    -0.67
    merie
    -0.66
    SpringBootTest
    -0.66
    LookAnd
    -0.64
     okuyayım
    -0.63
    POSITIVE LOGITS
     requests
    1.04
     getRequest
    1.04
     Request
    0.99
     request
    0.97
     Requests
    0.95
    getRequest
    0.91
    Requests
    0.90
     REQUEST
    0.89
    requests
    0.89
    REQUEST
    0.85
    Activations Density 0.074%

    No Known Activations