© 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. 9-GEMMASCOPE-RES-16K
    11. 5886
    Prev
    Next
    INDEX
    Explanations

    words related to installation and support services

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

    Installation, setup, or service by an engineer/installer

    np_acts-logits-general · gemini-2.0-flash

    installation and service process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.77
    DockStyle
    -0.62
    TagMode
    -0.56
    NewReader
    -0.51
    KURZBESCHREIBUNG
    -0.50
     createSlice
    -0.49
    
    -0.48
    PageModule
    -0.47
    ContextHolder
    -0.45
    EndContext
    -0.43
    POSITIVE LOGITS
     Installation
    0.57
    Installation
    0.54
     installation
    0.54
    installation
    0.52
     installer
    0.51
     installers
    0.48
     install
    0.47
     installing
    0.46
     Installations
    0.46
     Installer
    0.46
    Activations Density 0.408%

    No Known Activations