© 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. 33-GEMMASCOPE-RES-16K
    11. 6480
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     navideño
    -0.56
     productividad
    -0.55
     telefónica
    -0.53
     sanciones
    -0.52
     alimentaria
    -0.52
     corrupción
    -0.51
     alcanzado
    -0.50
     satisfecho
    -0.49
     navideña
    -0.49
     denuncias
    -0.48
    POSITIVE LOGITS
     Cell
    0.67
     Peer
    0.63
     Base
    0.62
     Child
    0.61
     My
    0.60
     Abstract
    0.60
     Body
    0.60
     Car
    0.59
     Game
    0.59
     Home
    0.58
    Activations Density 0.798%

    No Known Activations