© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3149
    Prev
    Next
    INDEX
    Explanations

    descriptive details about physical structures and decorations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.65
    verwijspagina
    -0.61
    úgó
    -0.54
    KommentareTeilen
    -0.53
    BufferException
    -0.53
    OGND
    -0.53
    AntiForgeryToken
    -0.50
    transQ
    -0.50
    oa̍t
    -0.50
    SpringRunner
    -0.49
    POSITIVE LOGITS
     covered
    1.25
     adorned
    1.16
     decorated
    1.11
     coated
    1.05
     bede
    1.00
     decked
    1.00
     clad
    0.91
     embellished
    0.90
     topped
    0.89
     Covered
    0.89
    Activations Density 0.551%

    No Known Activations