© 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. 7-GEMMASCOPE-RES-16K
    11. 14250
    Prev
    Next
    INDEX
    Explanations

    references to physical movement or positioning involving 'back'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaynağından
    -0.39
    pexpr
    -0.36
     suspensions
    -0.35
     Ig
    -0.33
     udaler
    -0.32
     poached
    -0.30
     cash
    -0.30
     hanged
    -0.30
     جوش
    -0.30
    sizeCache
    -0.29
    POSITIVE LOGITS
     backwards
    0.98
     назад
    0.94
     backward
    0.94
     back
    0.92
    back
    0.89
     indietro
    0.88
     îna
    0.85
     Backward
    0.82
     BACK
    0.82
     zurück
    0.81
    Activations Density 0.293%

    No Known Activations