© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31493
    Prev
    Next
    INDEX
    Explanations

    terms related to names or identifiers, possibly of people or objects

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

    tokens ending in f

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     يتيمه
    -0.99
    Portale
    -0.85
    gonic
    -0.84
    GraphicsUnit
    -0.78
    er
    -0.77
    prelude
    -0.77
     Camara
    -0.73
    aio
    -0.70
    Xna
    -0.69
    PickerController
    -0.67
    POSITIVE LOGITS
     Haf
    0.97
     Tuf
    0.96
     Bof
    0.96
    Bif
    0.95
     Bif
    0.94
     Cef
    0.92
    Coff
    0.92
     Duf
    0.91
     Tuff
    0.91
    iff
    0.91
    Activations Density 0.492%

    No Known Activations