© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5603
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate something that is concealed or not immediately visible

    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
    lamps
    -0.57
    viewers
    -0.57
    ătoare
    -0.54
     y
    -0.53
    Portale
    -0.52
    vri
    -0.52
     TS
    -0.52
     Lim
    -0.52
    чие
    -0.52
    োগ
    -0.51
    POSITIVE LOGITS
     behind
    3.56
     Behind
    3.33
    behind
    3.31
    Behind
    3.28
     BEHIND
    3.16
     derrière
    2.74
     detrás
    2.51
     dietro
    2.36
     bakom
    2.19
     خلف
    1.86
    Activations Density 0.040%

    No Known Activations