© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6965
    Prev
    Next
    INDEX
    Explanations

    references to mobile application features and user interactions

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

    Code, lists, or series names

    np_acts-logits-general · gemini-2.0-flash

    Series, 劇, shows, movies

    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
     fumée
    -0.37
     humo
    -0.33
     cuantos
    -0.31
     simplicité
    -0.31
     garantías
    -0.30
     poignée
    -0.29
     Entwicklungs
    -0.29
     poursuite
    -0.29
     vuestro
    -0.29
     mayores
    -0.29
    POSITIVE LOGITS
    ValueStyle
    0.65
    exitRule
    0.65
    ⤹
    0.63
    dify
    0.63
     purpoſe
    0.62
    tagHelperRunner
    0.61
     queſto
    0.59
     myſelf
    0.59
     AssemblyCulture
    0.58
    ೢ
    0.58
    Activations Density 0.190%

    No Known Activations