© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1359
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process of installing software or components

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

    Software installation instructions

    np_acts-logits-general · gemini-2.0-flash

    install

    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
    Notae
    -0.61
     RIPRODUZIONE
    -0.60
    PyExc
    -0.58
    RectangleBorder
    -0.55
    awaiter
    -0.54
    frå
    -0.53
     TextBox
    -0.52
    떻
    -0.52
    MessageOf
    -0.51
    Cordialement
    -0.51
    POSITIVE LOGITS
     installation
    1.12
     Install
    1.08
     install
    1.08
    Install
    1.07
     Installation
    1.05
     installed
    1.02
     installations
    1.01
     Installed
    1.00
    install
    1.00
    Installation
    0.99
    Activations Density 0.068%

    No Known Activations