© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5552
    Prev
    Next
    INDEX
    Explanations

    active verbs and actions related to conflict or movement

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

    Action immediately following "and" or "went"

    np_acts-logits-general · gemini-2.0-flash

    actions following movement verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.79
     disambiguazione
    -0.74
    MessageTagHelper
    -0.67
     snippetHide
    -0.65
     pinulongan
    -0.63
     EconPapers
    -0.60
    bootstrapcdn
    -0.60
     argint
    -0.60
    providedIn
    -0.59
     AssemblyCompany
    -0.58
    POSITIVE LOGITS
     rush
    0.60
     rushed
    0.55
     rushing
    0.52
     grab
    0.49
     reach
    0.48
     rushes
    0.45
     Reach
    0.44
     approach
    0.43
     grabbed
    0.42
     Rush
    0.41
    Activations Density 0.219%

    No Known Activations