© 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. 36-GEMMASCOPE-RES-16K
    11. 11318
    Prev
    Next
    INDEX
    Explanations

    the presence of sentences related to decision-making processes or notable actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.94
    SharedDtor
    -0.91
    ंदीखरीदारी
    -0.88
    IntoConstraints
    -0.85
     ProtoMessage
    -0.84
    +#+#
    -0.83
     Normdatei
    -0.81
    featureID
    -0.80
    \{\\
    -0.79
     AssemblyCulture
    -0.79
    POSITIVE LOGITS
    However
    0.68
     However
    0.63
    They
    0.60
    But
    0.58
    Anyway
    0.56
    Fortunately
    0.55
    If
    0.55
    When
    0.53
    Therefore
    0.53
     Toutefois
    0.53
    Activations Density 2.405%

    No Known Activations