© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6407
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to cryptography and encryption algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     b
    -1.27
     p
    -1.23
     d
    -1.18
     f
    -1.18
     c
    -1.18
     v
    -1.16
     t
    -1.16
     j
    -1.16
     r
    -1.16
     h
    -1.13
    POSITIVE LOGITS
     ainfi
    0.53
     pouvoit
    0.53
     feroit
    0.53
     étoit
    0.52
    حوالہ
    0.51
     démocr
    0.50
     auroit
    0.49
    ValueGenerated
    0.48
    httphttps
    0.47
    Gambas
    0.46
    Activations Density 1.880%

    No Known Activations