© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    terms associated with programming and data management

    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
     ſever
    -0.63
     ſind
    -0.56
     faſt
    -0.55
     ſche
    -0.54
     houſe
    -0.54
     pity
    -0.54
     purpoſe
    -0.52
     للمعارف
    -0.51
     ſch
    -0.50
     raiſ
    -0.49
    POSITIVE LOGITS
    principalColumn
    0.57
     SwitchCompat
    0.52
    ViewImports
    0.48
    Personendaten
    0.46
     intptr
    0.45
     =
    0.43
     huom
    0.42
     ویکی‌پدی
    0.41
    첩
    0.40
     snippetHide
    0.40
    Activations Density 0.208%

    No Known Activations