© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1726
    Prev
    Next
    INDEX
    Explanations

    the word "manifest" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.80
    XmlAttribute
    -0.73
     Rowe
    -0.72
     OSError
    -0.70
     debtor
    -0.64
     glasses
    -0.62
    hti
    -0.62
     Debt
    -0.62
    glasses
    -0.61
    WebGL
    -0.61
    POSITIVE LOGITS
     manifest
    2.10
    manifest
    1.93
     Manifest
    1.89
    Manifest
    1.89
    manif
    1.68
     manifests
    1.64
     manifesting
    1.53
     manifested
    1.52
    Manif
    1.45
     Manif
    1.40
    Activations Density 0.043%

    No Known Activations