© 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. 31-GEMMASCOPE-RES-131K
    11. 24242
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to machinery and measurement in engineering

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

    combination and manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.74
     nonUne
    -0.63
    ReusableCell
    -0.63
    Personendaten
    -0.57
    ChildScrollView
    -0.57
    دانشنامهٔ
    -0.55
    ">//
    -0.55
     OnInit
    -0.52
     Drapeau
    -0.51
     resourceCulture
    -0.51
    POSITIVE LOGITS
     combinations
    0.98
     kombinasi
    0.86
    combinations
    0.84
     carefully
    0.81
     combinação
    0.80
     combination
    0.79
     combinación
    0.78
     manipulations
    0.75
     Kombination
    0.74
     manipulation
    0.74
    Activations Density 0.158%

    No Known Activations