© 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. 5564
    Prev
    Next
    INDEX
    Explanations

    key points and highlights related to economic conditions or statistics

    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
    ⟬
    -0.81
     Савезне
    -0.71
     XNUMX
    -0.59
    ကိုးကား
    -0.59
     سكانية
    -0.57
     fuckin
    -0.56
     fucking
    -0.56
    Chham
    -0.55
    NUMX
    -0.54
    SOUNDBITE
    -0.54
    POSITIVE LOGITS
     •
    1.84
    •
    1.72
     ·
    1.31
    ・
    1.26
    ·
    1.18
    ●
    1.18
     ●
    1.13
     ・
    1.09
    €¢
    1.06
     *
    1.02
    Activations Density 0.674%

    No Known Activations