Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 68589
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to love, beauty, and moral themes

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

    abstract concepts and societal themes

    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
     Worldwide
    -0.48
    orphic
    -0.46
    vero
    -0.46
    MessageOf
    -0.45
    ないように
    -0.45
    Zx
    -0.44
     Omni
    -0.42
     Mano
    -0.42
    esco
    -0.42
    lagten
    -0.42
    POSITIVE LOGITS
    ActionCreators
    0.46
    Referencies
    0.46
    MessageTagHelper
    0.42
     juſ
    0.42
    PYX
    0.39
     reputación
    0.39
     seems
    0.39
    protoimpl
    0.38
     sufrido
    0.37
    basicConfig
    0.36
    Activations Density 0.184%

    No Known Activations