© 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. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1121
    Prev
    Next
    INDEX
    Explanations

    instances of the word "man" and various references to "thing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.54
     interesar
    -0.51
    XmlAccessType
    -0.51
    énéral
    -0.49
    CharStream
    -0.49
     BeautifulSoup
    -0.49
     Sơ
    -0.48
    Dichlorobenzene
    -0.47
     Mô
    -0.47
    ########.
    -0.47
    POSITIVE LOGITS
    fortawesome
    0.84
    TypedDataSet
    0.66
    QMetaType
    0.63
    Хьажоргаш
    0.63
     referenties
    0.61
    UnknownFieldSet
    0.61
    Personendaten
    0.60
    ngths
    0.59
     digress
    0.59
     SqlCommand
    0.58
    Activations Density 0.296%

    No Known Activations