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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4375
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or acronyms, particularly in formal contexts

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

    Two or three letter strings

    np_acts-logits-general · gemini-2.0-flash

    outsourcing, Tsang, Selo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erver
    -0.68
    möglichkeiten
    -0.67
    o
    -0.65
    ola
    -0.65
    u
    -0.64
    uite
    -0.62
    
    -0.61
    upply
    -0.59
    ube
    -0.59
    ology
    -0.59
    POSITIVE LOGITS
    labelledby
    0.59
     ujednoznacz
    0.56
    Alike
    0.56
    setContentView
    0.56
     оригіналу
    0.55
     GenerationType
    0.54
    quedas
    0.50
    uxxxx
    0.49
    CppCodeGen
    0.48
     hObject
    0.48
    Activations Density 0.285%

    No Known Activations