© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 757
    Prev
    Next
    INDEX
    Explanations

    phrases related to security and privacy assurances

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

    after certain verbs/actions

    np_acts-logits-general · gemini-2.0-flash

    describing actions and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PropertyChanging
    -0.50
    ttemberg
    -0.47
    RegistryLite
    -0.46
     BrowserModule
    -0.42
    MockMvc
    -0.42
     initComponents
    -0.42
    OCCURRED
    -0.42
    ilung
    -0.41
    ">//
    -0.40
    tonode
    -0.39
    POSITIVE LOGITS
     arşivlendi
    0.56
     bezeichneter
    0.42
    heureusement
    0.40
    !*\
    0.40
    eloma
    0.40
    voort
    0.40
    stände
    0.37
     ComVisible
    0.37
    hilangan
    0.37
    scaling
    0.36
    Activations Density 0.255%

    No Known Activations