© 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. 33-GEMMASCOPE-RES-16K
    6. 8510
    Prev
    Next
    INDEX
    Explanations

    references to prior studies and research

    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
    當初
    -0.46
     poffible
    -0.44
     itſelf
    -0.42
    ulemon
    -0.42
     defStyleAttr
    -0.42
     thereafter
    -0.40
     vidare
    -0.39
    到时候
    -0.39
     künftig
    -0.39
     potem
    -0.38
    POSITIVE LOGITS
     successes
    0.56
     generations
    0.55
     versions
    0.55
     editions
    0.55
     incarnation
    0.54
     attempts
    0.52
    版本的
    0.52
     incar
    0.52
     évek
    0.51
    itisation
    0.51
    Activations Density 0.271%

    No Known Activations