© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5502
    Prev
    Next
    INDEX
    Explanations

    references to servers and related errors

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

    "Server" followed by errors or configuration

    np_acts-logits-general · gemini-2.0-flash

    server errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.78
    ➡
    -0.72
    PrototypeOf
    -0.72
    hhhhhhhh
    -0.68
    InteropServices
    -0.68
     INTERESAR
    -0.67
     EnglishChoose
    -0.66
    gleich
    -0.65
     taches
    -0.64
    XmlType
    -0.63
    POSITIVE LOGITS
     servers
    1.34
     Servers
    1.24
     SERVER
    1.19
     smtplib
    1.15
     Server
    1.14
    Servers
    1.10
     server
    1.09
    SERVER
    1.09
    erver
    0.99
    Server
    0.98
    Activations Density 0.114%

    No Known Activations