© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 9815
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to protein purification and analysis

    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
    BuildContext
    -0.35
    orianCalendar
    -0.32
    못
    -0.31
    StandardCharsets
    -0.30
    цездатний
    -0.29
     Völ
    -0.29
    rekli
    -0.28
    CreateIndex
    -0.27
    ArgsConstructor
    -0.27
    Kha
    -0.27
    POSITIVE LOGITS
     purification
    1.42
     Purification
    1.32
     purify
    1.23
    Purification
    1.19
     purified
    1.18
     isolation
    1.16
     purific
    1.14
     purifying
    1.13
    puri
    1.13
     Isolation
    1.13
    Activations Density 1.872%

    No Known Activations