© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6890
    Prev
    Next
    INDEX
    Explanations

    references to the Scriptures and their teachings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before auxiliary verbs (can, is, will)

    np_acts-logits-general · gemini-2.0-flash

    divine truth and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    audiovisuel
    -0.43
    transQ
    -0.43
     flirt
    -0.42
     Flux
    -0.42
    delwed
    -0.42
     disrespectful
    -0.41
    nocchi
    -0.41
     regrettable
    -0.41
     snub
    -0.41
     masturb
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.49
    ValueStyle
    0.46
    principalColumn
    0.42
     promesa
    0.42
     promised
    0.42
    artifactId
    0.42
     promises
    0.40
     promesse
    0.39
     dirigez
    0.39
     direccion
    0.39
    Activations Density 0.147%

    No Known Activations