© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12485
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to conditional logic and flow control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.05
     queſto
    -0.98
    ſicht
    -0.94
    iſche
    -0.92
    niſſe
    -0.90
    ࿊
    -0.90
     FacebookSign
    -0.90
    iſchen
    -0.90
    <unused8>
    -0.89
    <unused41>
    -0.89
    POSITIVE LOGITS
    ↵
    0.31
     spagno
    0.28
     venezolano
    0.27
    ↵↵
    0.27
     bambú
    0.26
     piedras
    0.25
    的
    0.25
    0.24
    　
    0.24
     bandeira
    0.24
    Activations Density 0.470%

    No Known Activations