© 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-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 6556
    Prev
    Next
    INDEX
    Explanations

    references to shifts in time or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    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
     here
    -2.09
    here
    -1.60
     здесь
    -1.59
     allí
    -1.55
     aquí
    -1.52
     Here
    -1.48
     Allí
    -1.48
    在那里
    -1.48
     HERE
    -1.46
    Here
    -1.45
    POSITIVE LOGITS
    enumi
    0.68
    enumii
    0.67
     disambiguazione
    0.59
    DOCTYPE
    0.57
    TestingModule
    0.56
    __(/*!
    0.53
    SqlSession
    0.52
    astă
    0.51
    ValueStyle
    0.50
    PointerException
    0.49
    Activations Density 0.288%

    No Known Activations