© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 3225
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to various forms of support, both in personal and organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    support
    -0.85
     support
    -0.84
    supported
    -0.81
     supported
    -0.79
    supporting
    -0.76
     SUPPORT
    -0.75
     supporting
    -0.75
     supports
    -0.75
    Supporting
    -0.75
    SUPPORT
    -0.73
    POSITIVE LOGITS
     mechanisms
    0.58
     structures
    0.54
    ByVersion
    0.52
     networks
    0.51
     financially
    0.49
     efforts
    0.49
     Mechanisms
    0.49
     Structures
    0.48
     ModelExpression
    0.48
     structure
    0.46
    Activations Density 0.236%

    No Known Activations