© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 74406
    Prev
    Next
    INDEX
    Explanations

    phrases expressing emotional states or experiences

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

    something followed by description

    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
    AddTagHelper
    -0.38
     getUsername
    -0.35
    çois
    -0.33
     excès
    -0.33
     dingin
    -0.31
     Bretaña
    -0.30
    yty
    -0.30
    bek
    -0.30
     enged
    -0.30
     calls
    -0.29
    POSITIVE LOGITS
     something
    1.29
    something
    1.26
    Something
    1.23
     Something
    1.22
     SOMETHING
    1.09
     somethin
    1.07
     qualcosa
    0.93
     sesuatu
    0.82
     quelque
    0.80
     ceva
    0.79
    Activations Density 0.067%

    No Known Activations