© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2310
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or specific suffixes in words, particularly variations of "ina" and affixes like "ier" and "grove"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embri
    -0.48
    Initializable
    -0.44
    TCHAR
    -0.42
     transfieras
    -0.42
    miet
    -0.39
     Италијани
    -0.39
    openzeppelin
    -0.39
    quatch
    -0.39
     fecond
    -0.39
     reven
    -0.39
    POSITIVE LOGITS
    ina
    0.81
    INA
    0.69
    ной
    0.59
     dispose
    0.54
     tidy
    0.54
    ena
    0.52
     neat
    0.52
     fork
    0.50
     disposing
    0.50
     Protocols
    0.49
    Activations Density 0.559%

    No Known Activations