© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 19459
    Prev
    Next
    INDEX
    Explanations

    verbs that suggest actions, processes, or roles related to different subjects or contexts

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

    verbs ending in -ing describing actions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tagHelperRunner
    -0.64
     mergeFrom
    -0.56
    URLException
    -0.54
    StringCopy
    -0.52
     affari
    -0.49
     biais
    -0.48
    +#+#
    -0.47
     Infór
    -0.47
    AdapterView
    -0.45
     OkHttpClient
    -0.45
    POSITIVE LOGITS
     giving
    0.60
    rowing
    0.58
     taking
    0.58
     needing
    0.57
     appearing
    0.56
     impacting
    0.56
     attending
    0.56
     offering
    0.56
     presenting
    0.56
     providing
    0.55
    Activations Density 0.265%

    No Known Activations