© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 204
    Prev
    Next
    INDEX
    Explanations

    discussions around the economic impacts and reforms related to energy and health care systems

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

    old and inefficient homes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    webElement
    -0.48
    AddTagHelper
    -0.47
    StoryboardSegue
    -0.46
    ArgsConstructor
    -0.45
    enterOuterAlt
    -0.44
    PreExecute
    -0.42
    OuterAlt
    -0.40
    AfterViewInit
    -0.40
     ModelExpression
    -0.40
     Normdatei
    -0.40
    POSITIVE LOGITS
     outdated
    0.97
     antiquated
    0.88
     archaic
    0.84
    Outdated
    0.72
     obsolete
    0.68
     old
    0.68
    chaic
    0.63
     inefficient
    0.63
     vecchi
    0.60
     inadequacy
    0.59
    Activations Density 0.141%

    No Known Activations